Public recordModerate
Software health reportschema 0.27.0 · metrics 1.13.0 · 2026-07-27 13:12 UTC
rmovva / HypotheSAEs
HypotheSAEs: hypothesizing interpretable relationships in text datasets using sparse autoencoders. https://arxiv.org/abs/2502.04382
rmovva/HypotheSAEs holds a health index of 53 out of 100, placing it in the Moderate band. It scores highest on Vitality (69/100) and lowest on AI Readiness (24/100). It was last updated 3 days ago. A single contributor accounts for most of its recent work.
53
overall / 100Software health index
Metrics are grouped into weighted categories on one standardized 1–100 scale. Overall starts as their weighted mean; when public evidence triggers the High-Risk Jurisdiction Policy, the rating is adjusted and receives an At risk ceiling of 49. AI Readiness sits outside the overall score.
53
Excellent85-100Exemplary; meets essentially all checked criteria
Good70-84Healthy; minor gaps
Moderate50-69Acceptable with notable gaps; review recommended
At risk30-49Significant weaknesses; adoption warrants caution
Critical1-29Severe problems (abandoned, single-maintainer, no hygiene)
Score profile
Each axis is a category. The shape matters more than the average — a healthy subject fills the whole shape, while a spike-and-crater profile means strength in one dimension is masking risk in another.
Ownership
Raj MovvaPersonal account
20 followers33 public repossince Feb 2016UC Berkeley
This repository is owned by a personal account. A single-owner project carries more continuity risk than an organization-backed one.
Package ecosystems
| Registry | Package | Version | Downloads / mo | Versions | Last publish |
|---|---|---|---|---|---|
| PyPI | hypothesaes | 2.0.1 | 240 | 13 | 24 days ago |
Metrics by category
Vitality
Is the project alive — is code being written and are releases shipping?
69
Development activity
62Moderate
How it's scored
| 36/36 | Push recency — last push 3 days ago |
| 7.6/36 | Commit cadence — 11/52 weeks with commits |
| 15.3/18 | Commit volume — 50 commits in the last year |
| 3/10 | OpenSSF Scorecard: Maintained — 3 commit(s) and 1 issue activity found in the last 90 days -- score normalized to 3 |
Inputs used
| commits_last_year | 50 |
| human_commit_share | 1 |
| days_since_last_push | 3 |
| active_weeks_last_year | 11 |
Release discipline
80Good
How it's scored
| 16.2/27 | Ships releases — 7 version tags (no GitHub releases) |
| 36/36 | Release recency — latest release 24 days ago |
| 19.8/27 | Release cadence — a release every ~72.6 days |
| 0/10 | OpenSSF Scorecard: Signed-Releases — no data |
Inputs used
| releases_count | 7 |
| latest_release_tag | v2.0.1 |
| releases_from_tags | yes |
| days_since_latest_release | 24 |
| mean_days_between_releases | 72.6 |
Excluded from scoring (no data or not applicable): OpenSSF Scorecard: Signed-Releases. Remaining weights renormalized.
Community & Adoption
Does the project have users, downloads, attention, and a welcoming setup for contributors?
45
Popularity & adoption
44At risk
How it's scored
| 31.7/60 | Stars — 91 stars |
| 11.9/25 | Forks — 28 forks |
| 0/15 | Watchers — 2 watchers |
Inputs used
| forks | 28 |
| stars | 91 |
| watchers | 2 |
| growth_state | unverified |
| growth_factor_pct | 100 |
| growth_unverified_reason | no_history |
Community health
50Moderate
How it's scored
| 22.5/22.5 | README |
| 22.5/22.5 | License — recognized license (Apache-2.0) |
| 0/18 | CONTRIBUTING guide |
| 0/13.5 | Code of conduct |
| 0/7.2 | Issue template |
| 0/6.3 | PR template |
Inputs used
| has_readme | yes |
| has_license | yes |
| has_contributing | no |
| has_issue_template | no |
| has_code_of_conduct | no |
| has_pull_request_template | no |
Ecosystem adoption (downloads)
40At risk
How it's scored
| 31.8/80 | Monthly downloads — 240 downloads/month across pypi |
| 0/20 | Registry dependents — not reported by this ecosystem |
Inputs used
| packages | hypothesaes |
| dependents | — |
| ecosystems | pypi |
| total_downloads | — |
| monthly_downloads | 240 |
Excluded from scoring (no data or not applicable): Registry dependents. Remaining weights renormalized.
Sustainability & Governance
Will the project survive its people — bus factor, responsiveness, who backs it, and package upkeep?
57
Maintainer resilience (bus factor)
16Critical
How it's scored
| 9/54 | Bus factor — 1 contributor(s) cover half of all commits |
| 0.3/22.5 | Commit distribution — top contributor authored 99% of commits |
| 4.1/13.5 | Contributor breadth — 3 contributors |
| 3/10 | OpenSSF Scorecard: Contributors — project has 1 contributing companies or organizations -- score normalized to 3 |
Inputs used
| bus_factor | 1 |
| contributors_sampled | 3 |
| top_contributor_share | 0.987 |
How it's scored
| 37.4/46.8 | Issue resolution — 80% of issues closed |
| 38.2/38.3 | PR acceptance — 5/5 decided PRs merged |
| 0/15 | OpenSSF Scorecard: Code-Review — Found 2/30 approved changesets -- score normalized to 0 |
Inputs used
| merged_prs | 5 |
| open_issues | 1 |
| closed_issues | 4 |
| issue_closed_ratio | 0.8 |
| closed_unmerged_prs | 0 |
Ownership & stewardship
53Moderate
How it's scored
| 10/30 | Ownership backing — personal (user) account |
| 0/20 | Verified domain — not applicable to user accounts |
| 9.5/25 | Owner reach — 20 followers of rmovva |
| 23.2/25 | Track record — 33 public repos, account ~10 yr old |
Inputs used
| followers | 20 |
| owner_type | User |
| is_verified | — |
| owner_login | rmovva |
| public_repos | 33 |
| account_age_days | 3,814 |
Excluded from scoring (no data or not applicable): Verified domain. Remaining weights renormalized.
Package maintenance
100Excellent
How it's scored
| 25/25 | Published & resolvable — 1 package(s) on pypi |
| 35/35 | Publish recency — latest publish 24 days ago |
| 20/20 | Version history — 13 published versions |
| 20/20 | Not deprecated — active, not deprecated or yanked |
Inputs used
| packages | hypothesaes |
| ecosystems | pypi |
| any_deprecated | no |
| min_days_since_publish | 24 |
Engineering Quality
Are baseline engineering and documentation practices in place?
44
Engineering practices
24Critical
How it's scored
| 0/24 | CI workflows |
| 24/24 | Tests present |
| 0/16 | Linter config |
| 0/9.6 | Pre-commit hooks |
| 0/6.4 | .editorconfig |
| 0/20 | OpenSSF Scorecard: CI-Tests — 0 out of 3 merged PRs checked by a CI test -- score normalized to 0 |
Inputs used
| has_ci | no |
| has_tests | yes |
| has_editorconfig | no |
| has_linter_config | no |
| has_precommit_config | no |
Documentation
75Good
How it's scored
| 30/30 | README |
| 0/25 | Documentation directory |
| 15/15 | Documentation / homepage site — https://hypothesaes.org |
| 10/10 | Repository description |
| 10/10 | Topics — 6 topics |
| 10/10 | Wiki |
Inputs used
| topics | ai-for-science, computational-social-science, interpretability, nlp, sparse-autoencoders, topic-modeling |
| has_wiki | yes |
| homepage | https://hypothesaes.org |
| has_readme | yes |
| has_docs_dir | no |
| has_description | yes |
Security
Are visible security and supply-chain practices strong, without unresolved high-risk jurisdiction exposure?
43
Security posture
29Critical
How it's scored
| 7.5/7.5 | Binary-Artifacts — no binaries found in the repo |
| 0/7.5 | Branch-Protection — branch protection not enabled on development/release branches |
| 0/2.5 | CI-Tests — 0 out of 3 merged PRs checked by a CI test -- score normalized to 0 |
| 0/2.5 | CII-Best-Practices — no effort to earn an OpenSSF best practices badge detected |
| 0/7.5 | Code-Review — Found 2/30 approved changesets -- score normalized to 0 |
| 0.8/2.5 | Contributors — project has 1 contributing companies or organizations -- score normalized to 3 |
| 0/10 | Dangerous-Workflow — no data |
| 0/7.5 | Dependency-Update-Tool — no update tool detected |
| 0/5 | Fuzzing — project is not fuzzed |
| 2.5/2.5 | License — license file detected |
| 2.2/7.5 | Maintained — 3 commit(s) and 1 issue activity found in the last 90 days -- score normalized to 3 |
| 0/5 | Packaging — no data |
| 0/5 | Pinned-Dependencies — no data |
| 0/5 | SAST — SAST tool is not run on all commits -- score normalized to 0 |
| 0/5 | Security-Policy — security policy file not detected |
| 0/7.5 | Signed-Releases — no data |
| 0/7.5 | Token-Permissions — no data |
| 7.5/7.5 | Vulnerabilities — 0 existing vulnerabilities detected |
Inputs used
| source | openssf_scorecard |
| checks_evaluated | 13 |
| scorecard_version | v5.5.0 |
| checks_inconclusive | 5 |
| scorecard_aggregate | 2.9 |
Excluded from scoring (no data or not applicable): dangerous_workflow, packaging, pinned_dependencies, signed_releases, token_permissions. Remaining weights renormalized.
Dependency advisories
100Excellent
How it's scored
| 35/35 | Direct dependencies free of known advisories — no direct dependency carries a known advisory |
| 25/25 | Indirect dependencies free of known advisories — no indirect dependency carries a known advisory |
| 0/40 | No advisories left outstanding — no advisory carries a publication date |
Inputs used
| source | osv |
| advisories | 0 |
| affected_packages | 0 |
| assessed_packages | 145 |
| unassessed_packages | 0 |
| affected_by_severity | none |
| direct_affected_packages | 0 |
Excluded from scoring (no data or not applicable): No advisories left outstanding. Remaining weights renormalized. Matched the pypi:hypothesaes@2.0.1 runtime dependency closure — what installing the published package pulls in — 145 packages. Reachability is not analyzed.
AI Readiness
How well is the repo equipped to be developed and maintained with AI coding agents? An independent, experimental badge — weight 0.0, so it is surfaced on its own and does not affect the overall health score.
24
Agent context & guidance
2Critical
How it's scored
| 0/45 | Agent instructions — no CLAUDE.md / AGENTS.md / editor rules |
| 0/15 | Machine-readable docs (llms.txt) |
| 2.1/40 | Legible commit history — 4 of 100 human commits state their intent (structured subject or explanatory body) |
Inputs used
| has_llms_txt | no |
| legible_history_share | 0.04 |
| agent_instruction_files | — |
| agent_instruction_max_bytes | — |
Verify loop (build / test / typecheck)
24Critical
How it's scored
| 0/18 | One-command bootstrap |
| 22/22 | Automated tests |
| 0/11 | Lint / format config |
| 0/11 | Static type checking |
| 0/10 | Reproducible environment |
| 0/10 | Demonstrated agent practice — no agent-authored commits among the last 100 |
| 0/8 | Automated maintenance — no automated dependency updates observed |
| 0/10 | OpenSSF Scorecard: Pinned-Dependencies — no data |
Inputs used
| has_nix | no |
| has_tests | yes |
| lockfiles | — |
| has_dockerfile | no |
| typed_language | no |
| bootstrap_files | — |
| has_devcontainer | no |
| has_linter_config | no |
| typecheck_configs | — |
| agent_commit_share | 0 |
| toolchain_manifests | — |
| dependency_bot_commit_share | 0 |
Excluded from scoring (no data or not applicable): OpenSSF Scorecard: Pinned-Dependencies. Remaining weights renormalized.
Code legibility for models
55Moderate
How it's scored
| 0/45 | Type-checkable code — Jupyter Notebook without a type-check config |
| 55/55 | Manageable file sizes — 0/19 source files over 60KB |
Inputs used
| primary_language | Jupyter Notebook |
| largest_source_bytes | 21,515 |
| source_files_sampled | 19 |
| oversized_source_files | 0 |
Machine-readable interfaces
40At risk
How it's scored
| 0/40 | API schema (OpenAPI/GraphQL/proto) |
| 0/20 | MCP server |
| 40/40 | Runnable examples — notebooks |
Inputs used
| example_dirs | notebooks |
| has_mcp_signal | no |
| api_schema_files | — |
Key facts
91GitHub stars
3contributors
50commits, last 12 months
3days since last push
7releases
1bus factor
1open issues
PyPIpackage ecosystems
Data collection warnings
- Star history unavailable: GitHub GraphQL error: Resource not accessible by personal access token
More detail
Star and fork history 0 ★ / 28 ⇿
0Stars
28Forks
7Releases
When each star and fork was added, collected from GitHub and bucketed by day. Cumulative growth sits directly above the daily additions it is made of, so the two read against each other: steady organic accretion looks nothing like an abrupt, short-lived burst. Where that difference is measurable, it is reported as growth authenticity.
Major 2Minor 4Patch 1
Each point covers 2 days.
OpenSSF Scorecard 2.9 / 10
2.9aggregate
Independent, tool-agnostic security assessment from the open-source OpenSSF Scorecard. Each check rewards a security practice, not a specific vendor's tool. Checks Scorecard could not determine are marked n/a and excluded from the security score (never counted as zero).
| 10 | Binary-Artifacts | no binaries found in the repo |
| 0 | Branch-Protection | branch protection not enabled on development/release branches |
| 0 | CI-Tests | 0 out of 3 merged PRs checked by a CI test -- score normalized to 0 |
| 0 | CII-Best-Practices | no effort to earn an OpenSSF best practices badge detected |
| 0 | Code-Review | Found 2/30 approved changesets -- score normalized to 0 |
| 3 | Contributors | project has 1 contributing companies or organizations -- score normalized to 3 |
| n/a | Dangerous-Workflow | no workflows found |
| 0 | Dependency-Update-Tool | no update tool detected |
| 0 | Fuzzing | project is not fuzzed |
| 10 | License | license file detected |
| 3 | Maintained | 3 commit(s) and 1 issue activity found in the last 90 days -- score normalized to 3 |
| n/a | Packaging | packaging workflow not detected |
| n/a | Pinned-Dependencies | no dependencies found |
| 0 | SAST | SAST tool is not run on all commits -- score normalized to 0 |
| 0 | Security-Policy | security policy file not detected |
| n/a | Signed-Releases | no releases found |
| n/a | Token-Permissions | No tokens found |
| 10 | Vulnerabilities | 0 existing vulnerabilities detected |
All dependencies 17
Full resolved dependency set from the GitHub dependency graph: 0 direct and 17 indirect (transitive) packages. The transitive closure is complete when the repository commits a lockfile.
| Registry | Package | Version | Relation |
|---|---|---|---|
| PyPI | accelerate | — | indirect |
| PyPI | jmespath | — | indirect |
| PyPI | jupyter | — | indirect |
| PyPI | matplotlib | — | indirect |
| PyPI | numpy | — | indirect |
| PyPI | openai | — | indirect |
| PyPI | pandas | — | indirect |
| PyPI | pytest | — | indirect |
| PyPI | scikit-learn | — | indirect |
| PyPI | scipy | — | indirect |
| PyPI | sentence-transformers | — | indirect |
| PyPI | setuptools | — | indirect |
| PyPI | statsmodels | — | indirect |
| PyPI | tiktoken | — | indirect |
| PyPI | torch | — | indirect |
| PyPI | tqdm | — | indirect |
| PyPI | transformers | — | indirect |
Dependency advisories 0
Installing pypi:hypothesaes@2.0.1 pulls in 145 packages, direct and transitive: 0 carry known advisories, of which 0 are direct dependencies.
No known advisories affect the assessed dependencies.
An advisory means the version recorded in the dependency graph falls inside an advisory’s affected range. Reachability is not analysed, and the graph includes development and test pins — a finding may concern tooling rather than shipped software.
Raw JSON report machine-readable
{
"data": {
"repo": {
"topics": [
"ai-for-science",
"computational-social-science",
"interpretability",
"nlp",
"sparse-autoencoders",
"topic-modeling"
],
"is_fork": false,
"size_kb": 17296,
"has_wiki": true,
"homepage": "https://hypothesaes.org",
"languages": {
"Python": 134111,
"Jupyter Notebook": 2052287
},
"pushed_at": "2026-07-24T00:08:27Z",
"created_at": "2025-03-12T19:09:33Z",
"owner_type": "User",
"updated_at": "2026-07-24T00:08:32Z",
"description": "HypotheSAEs: hypothesizing interpretable relationships in text datasets using sparse autoencoders. https://arxiv.org/abs/2502.04382",
"is_archived": false,
"is_disabled": false,
"license_spdx": "Apache-2.0",
"default_branch": "main",
"license_spdx_raw": "Apache-2.0",
"primary_language": "Jupyter Notebook",
"significant_languages": [
"Jupyter Notebook"
]
},
"owner": {
"blog": "www.rajivmovva.com",
"name": "Raj Movva",
"type": "User",
"login": "rmovva",
"company": "UC Berkeley",
"location": null,
"followers": 20,
"avatar_url": "https://avatars.githubusercontent.com/u/17256372?v=4",
"created_at": "2016-02-15T17:45:41Z",
"is_verified": null,
"public_repos": 33,
"account_age_days": 3814
},
"license": {
"state": "standard",
"spdx_id": "Apache-2.0",
"raw_spdx": "Apache-2.0",
"file_present": true,
"scorecard_found": true,
"profile_has_license": true
},
"activity": {
"releases": [
{
"tag": "v2.0.1",
"kind": "patch",
"published_at": "2026-07-02T18:10:43Z"
},
{
"tag": "v2.0.0",
"kind": "major",
"published_at": "2026-03-08T01:04:17Z"
},
{
"tag": "v1.1.0",
"kind": "minor",
"published_at": "2025-10-29T22:48:12Z"
},
{
"tag": "v1.0.0",
"kind": "major",
"published_at": "2025-09-15T22:54:41Z"
},
{
"tag": "v0.3.0",
"kind": "minor",
"published_at": "2025-07-29T06:52:17Z"
},
{
"tag": "v0.2.0",
"kind": "minor",
"published_at": "2025-05-04T01:34:29Z"
},
{
"tag": "v0.1.0",
"kind": "minor",
"published_at": "2025-04-22T20:41:16Z"
}
],
"recent_commits": [
{
"oid": "706d8979c71befe8e3151f51a8d4dbf87d4d7e41",
"body": "…nality (#12)\n\n* Updated separation score metric\n* Adding additional annotation funtionality",
"is_bot": false,
"headline": "Updated separation score metric & added additional annotation functio…",
"author_name": "adityad2123",
"author_login": "adityad2123",
"committed_at": "2026-07-24T00:08:27Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "dff36e4b6aefa16f47ac3bf82a5838395bd144c4",
"body": null,
"is_bot": false,
"headline": "Bump version: 2.0.1",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2026-07-02T18:10:43Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "4573abd87482ad3f02f850e0ca38897cac3e699b",
"body": null,
"is_bot": false,
"headline": "Fix interpretation precision metric",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2026-05-25T23:27:10Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "36d012d65ea46a98c7778b4002acf01ee64f628f",
"body": "* migrate llm client to responses api with openai-compatible base url\n\n* unify annotation and interpretation on api-based llm inference\n\n* update docs and tests for openai-compatible local endpoint flow\n\n* clarify local quickstart notebook note for unified api path\n\n* set uncapped token defaults and\n[…]\nble high matmul precision for local embeddings\n\n* Make vLLM optional for main install\n\n* Run through of local notebook using vLLM server\n\n* Remove in-process vLLM inference path\n\n* Bump version: 2.0.0",
"is_bot": false,
"headline": "2.0.0: unify local LLM support on OpenAI-compatible serving (#11)",
"author_name": "Raj Movva",
"author_login": "rmovva",
"committed_at": "2026-03-08T01:04:17Z",
"body_truncated": true,
"is_coding_agent": false
},
{
"oid": "a97898986e2e650dd1a9d186bbc3953d928c5ca2",
"body": null,
"is_bot": false,
"headline": "Update Python badge range",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-10-29T22:59:33Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "0e4098bd4cd47f07ab5cac8d328c00a741e7d7d2",
"body": null,
"is_bot": false,
"headline": "Ignore agent guide file",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-10-29T22:53:59Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "10def8e108fdd5d2e0811ad0747ad158730143e6",
"body": null,
"is_bot": false,
"headline": "Bump version: 1.1.0",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-10-29T22:48:12Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "a43671a256545fd553c8e566832838cbb131793b",
"body": null,
"is_bot": false,
"headline": "shutdown vLLM engine after testing",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-10-29T22:45:10Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "1387a3082b398ca1b13708c6292f62e6ef803c74",
"body": "….14 currently doesn't work)",
"is_bot": false,
"headline": "Make tests more robust / fix bugs; allow Python versions 3.10-3.13 (3…",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-10-29T22:21:54Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "dcd3ab91e6b749bfc7647842b2028c6ec2c81f9f",
"body": "…ations",
"is_bot": false,
"headline": "Increment version to 1.0.0; remove support for get_multiple_sae_activ…",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-09-15T22:54:41Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "4d8be7369ff0103dc19f1085ca496f5c363613d1",
"body": null,
"is_bot": false,
"headline": "Document Batch Top-K activation function + add to quickstart",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-09-15T22:23:48Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "00c9e3fb8db7f1a9d27887989614ec1c872f25b6",
"body": null,
"is_bot": false,
"headline": "Add option to use BatchTopK instead of TopK",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-09-15T21:52:19Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "4e1dbc5ece17f6b2efa00dcd6762e4d232882d60",
"body": null,
"is_bot": false,
"headline": "add bair commons notice",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-09-10T22:26:17Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "c894c82d0d010afd54b8ca26c317f10e5b91c44f",
"body": null,
"is_bot": false,
"headline": "Bump version: 0.3.1",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-08-29T05:32:07Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "1e0d7e9f43213af2ba49c2741a61c0825404e109",
"body": null,
"is_bot": false,
"headline": "Update quickstart nb",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-08-29T05:27:37Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "39ae7af15cd56338bd9fe771bded68b4714ced3d",
"body": null,
"is_bot": false,
"headline": "Fix Python versioning (currently <3.13 due to scipy bug)",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-08-29T04:38:02Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "22a756dbf71906462dcef1e67600a5ebe8d9771b",
"body": null,
"is_bot": false,
"headline": "Cache prompts to avoid reloading prompt file",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-08-29T04:37:48Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "766e37142b007af7eb601eb3d578aa29b3eb58ce",
"body": null,
"is_bot": false,
"headline": "Store OpenAI client as a global to avoid re-initializing it",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-08-29T04:29:56Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "f364a0982a7fe5bdbe60082f6584869241cde95b",
"body": null,
"is_bot": false,
"headline": "Fix bug in computing neuron prevalences",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-08-28T07:02:38Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "25279cb8e06551a36ad6294702e38156bc494c8c",
"body": null,
"is_bot": false,
"headline": "README FAQ: rate limits + privacy",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-08-14T17:59:48Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "d0c959dcddbbdb6dd3f30399fee03a31d7065137",
"body": null,
"is_bot": false,
"headline": "Update README FAQ",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-08-14T17:49:08Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "06baeb1cf3e07170bd9e5bfebebca7ba6edc5bbc",
"body": null,
"is_bot": false,
"headline": "Add jmespath dependency for transformers/vllm",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-08-14T03:44:41Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "d2955fbe1a87c8f1ab42c9fe6bad43bd13ae4264",
"body": null,
"is_bot": false,
"headline": "include reasoning_effort param for gpt-5",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-08-10T06:23:19Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "d158297f84433f076bdf512b76826341f48293ae",
"body": null,
"is_bot": false,
"headline": "Specify python version <= 3.12 (3.13 causes conflicts)",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-08-10T05:52:32Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "b91425adb98fe22b818533a8f0c42a8c38242bc0",
"body": "…ity code to allow kwargs",
"is_bot": false,
"headline": "Set gpt-4.1-mini to default completion model; cleanup surface similar…",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-08-06T00:38:06Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "22fb957862c503edd36ca121378574da5b3f9b01",
"body": "Add torch device param to SAE constructor",
"is_bot": false,
"headline": "Allow torch.device selection (#7)",
"author_name": "Andre Shportko",
"author_login": "Antebe",
"committed_at": "2025-08-06T00:34:18Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "67c5a4e408dc3b96f0e0eeae4fe9a682e63df7e9",
"body": "…d OOM",
"is_bot": false,
"headline": "Move vLLM loading *after* embedding computation in quickstart to avoi…",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-31T21:16:06Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "bb10034a86fe89e26afc45e6129409ff0cee0ab2",
"body": "… is >0), and print prevalence",
"is_bot": false,
"headline": "support interpreting top N neurons ranked by prevalence (how often it…",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-30T18:25:08Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "a497503b1e0881dab6fd7c8ef49fabc2c65f4e52",
"body": null,
"is_bot": false,
"headline": "Fix directory name in quickstart",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-29T07:00:59Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "fd9a5ec359998220307856697ae2159caea4985a",
"body": null,
"is_bot": false,
"headline": "Rename data & experiments directories",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-29T07:00:16Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "309443c0834ee9ceee653dd525f4d7c5c174d96d",
"body": "Support local LLM use for neuron interpretation and concept annotation",
"is_bot": false,
"headline": "Merge pull request #6 from rmovva/llmlocal",
"author_name": "Raj Movva",
"author_login": "rmovva",
"committed_at": "2025-07-29T06:52:17Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "491d9686f25bf92088b2f7a0b6b11473a266c75d",
"body": null,
"is_bot": false,
"headline": "Bump version: 0.3.0",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-29T06:48:10Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "d2923de09bada6bb8d2b2c324f0e2eeec11ef281",
"body": null,
"is_bot": false,
"headline": "Substantial README cleanup",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-29T02:17:06Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "55814505a936e7434ffc12b0f412d2b21f8c5d8d",
"body": null,
"is_bot": false,
"headline": "Docs cleanup",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-29T01:48:04Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "85a36dd51d82d70b6830658d1aa417f64039dbfe",
"body": null,
"is_bot": false,
"headline": "Cleanup/finalize local LLM benchmarking results",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-29T01:35:10Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "4b9ca159ad3770b63a75025461de58dde2d54f1c",
"body": null,
"is_bot": false,
"headline": "Correct sampling params for 'o*' models",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-29T01:35:01Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "adb774cdf12c2326d7fb0ee93f6d83642009ee3e",
"body": null,
"is_bot": false,
"headline": "Add some notes about vLLM",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-28T22:56:53Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "2401a4ae6c3cbe0e3846835f360ffeb3774b6e1a",
"body": null,
"is_bot": false,
"headline": "Fix imports",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-28T16:40:11Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "56c9751d59fb80dc7b935a5bb3380782070f4d6f",
"body": null,
"is_bot": false,
"headline": "Update run through of detailed_usage notebok",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-28T16:39:49Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "55af8983f7631c3a8bd97f892628fc94f5034b6f",
"body": null,
"is_bot": false,
"headline": "Update README",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-28T06:50:35Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "0c8ee0079c9932cc86efa9aa154b4ed595d3ca0e",
"body": null,
"is_bot": false,
"headline": "Re-run quickstart with refactored code.",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-28T06:36:26Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "e39e5a854d024d4d1809638d0b8c29481fab687c",
"body": null,
"is_bot": false,
"headline": "Edit \"sae_source_info\" code",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-28T06:31:16Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "5a2c34dd1806c62511f9f80e210b47ce1b5a6a66",
"body": "…om 4o)",
"is_bot": false,
"headline": "Change quickstart default OpenAI models to gpt-4.1 / gpt-4.1-mini (fr…",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-28T06:03:05Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "9959d0973d97fd290d0faa7b05ad7bcce2d9fb7c",
"body": null,
"is_bot": false,
"headline": "fix tokenizer_kwargs",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-28T05:47:09Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "de22ee0662a2c69efdb352a5822332d34bdc4e61",
"body": null,
"is_bot": false,
"headline": "Fix bug where openAI models are not loaded in vLLM",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-28T05:43:24Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "c6c28ed5d4867809c966ad37dcef3881abe2187c",
"body": null,
"is_bot": false,
"headline": "push quickstart nb for local LLM",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-28T04:51:04Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "390cf8be6aa416e068a6c6332d00c15a04d28e4a",
"body": null,
"is_bot": false,
"headline": "Change names",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-28T00:37:14Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "4790181ad0ac90e72196bca7007bbe73175a25bf",
"body": null,
"is_bot": false,
"headline": "Change vLLM func to get_vllm_engine",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-28T00:36:43Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "6d90b4c05da2e63d448babce21063aa64043d4d2",
"body": null,
"is_bot": false,
"headline": "Set default tokens for thinking-style generations to 8192",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-28T00:35:35Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "ed7137d441f3f72585ee409db1c9806829c11de3",
"body": "…or vLLM)",
"is_bot": false,
"headline": "Manually pass through progress_desc to parallel_annotate (can't use f…",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-28T00:35:18Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "a4222953dbf34df3d34da16c03025e11d8c9c873",
"body": null,
"is_bot": false,
"headline": "Clear embedding model from GPU memory after embeddings are generated",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-27T23:38:01Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "e0182b9de0c519ac7d4b455cd318f5ed97d9ccf1",
"body": "…_sae()",
"is_bot": false,
"headline": "Remove extraneous annotator model parameter from quickstart.interpret…",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-27T23:37:35Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "ddb02815c6aa760db4a68211fcc28d689fca6610",
"body": null,
"is_bot": false,
"headline": "Bugfix (prompt_template_name --> annotate_prompt_name)",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-27T22:42:30Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "403b220d6b6e97eab50d291a6e2537e085655d41",
"body": null,
"is_bot": false,
"headline": "Removing annot caching from benchmarking script",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-27T22:36:33Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "75d176848e388a8feec4a25d8be0db4397054fc5",
"body": null,
"is_bot": false,
"headline": "Refactor local bencmarking annot/interp code a bit",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-27T22:33:14Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "2c7896ee408247809958c518d5022c9f59047b09",
"body": null,
"is_bot": false,
"headline": "Push autointerp result figures",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-25T05:25:38Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "7e556238749f7ec56d9981252cd6a467e77d5bb5",
"body": null,
"is_bot": false,
"headline": "Add script to score interp fidelities",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-24T17:10:38Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "cbac0d1360146e285a26a52f198b516a7ec217b3",
"body": null,
"is_bot": false,
"headline": "Rename variables for clearer kwargs",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-24T17:08:07Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "19a68c58823b6f3fc4d6cf3abdf0530560e92bd1",
"body": null,
"is_bot": false,
"headline": "Clarify the prompt_template variables to disambiguate interp/annotatoin",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-24T17:03:23Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "01e5df4c3d8624441d6431c8ae8b12321085336b",
"body": null,
"is_bot": false,
"headline": "Fix: select same neurons for every model for interp experiment",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-24T05:50:34Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "c33b0a16d8e914a57b6564b7582eda95181e2025",
"body": null,
"is_bot": false,
"headline": "Update interpretation benchmarking script",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-24T05:40:15Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "4fe764adbc1dbcb365ff9bed0e21a7a277bd9eb2",
"body": null,
"is_bot": false,
"headline": "fix bug: temperature=None doesn't work for vLLM",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-24T04:51:13Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "6dc2dd984b5cc0f84f39bc8dbff98d60d3238204",
"body": "…rams for vLLM",
"is_bot": false,
"headline": "Slight refactor to handling of temperature / max tokens / sampling pa…",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-23T23:57:39Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "3be7e4b63c9b30996e1377f6fb5d4ae015945865",
"body": null,
"is_bot": false,
"headline": "working on README update",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-23T23:57:22Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "3bbc17be0f6de9723f6ea0e8d1086ae1252872e5",
"body": null,
"is_bot": false,
"headline": "Change defaults to 4.1/4.1-mini for openai",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-23T21:51:15Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "ef614675f23a49a4af3eb6c31996d5c8c30357f7",
"body": null,
"is_bot": false,
"headline": "Skip \"None\" interpretations from scoring",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-23T21:41:03Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "7d770a9930f3fae1443333c634b7054f07ec9598",
"body": null,
"is_bot": false,
"headline": "Edit prompts, reduce example count",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-23T19:00:07Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "a4cb4e6c073eda6994fe080d417f44d1a634cce0",
"body": null,
"is_bot": false,
"headline": "Fix interp prompt for test, use more thinking tokens",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-23T18:18:52Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "33a5eefeae02b5bbc6853ad9762b07d1a01a7347",
"body": "…erp samples",
"is_bot": false,
"headline": "Use different random seed for each interpretation candidate's autoint…",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-23T18:18:07Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "f3cd87fa3d4a8fb822c41474c399b57f4a0bf9de",
"body": "…o think more concisely",
"is_bot": false,
"headline": "Fix parsing of thinking outputs; add new prompt to encourage models t…",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-23T18:03:05Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "4f5265cbcb12aaa6bf514fb715de77a16e20422f",
"body": null,
"is_bot": false,
"headline": "Fix bug in parsing autointerps from models with <think> tags",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-23T17:41:15Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "973abd7d312db64dd6e5087d36a7398279476989",
"body": null,
"is_bot": false,
"headline": "more local LLM testing code for interpretations now",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-23T06:16:20Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "5141230a17c5e2cd12cc4d890bc376a2aaf65248",
"body": null,
"is_bot": false,
"headline": "fix bug for nomic embeddings",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-23T06:14:51Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "d67d4ffb4dfe70c6dbe42bdc5a06de309298d645",
"body": null,
"is_bot": false,
"headline": "Pareto frontier of annotation quality vs. time taken",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-23T02:27:06Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "8036bf2bc5c4dbd07676937222a1dd6a8ea9472a",
"body": null,
"is_bot": false,
"headline": "use enable_thinking=False in tests",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-23T02:26:54Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "071a931db0937966bf6a9dcdbeccb197f767093b",
"body": null,
"is_bot": false,
"headline": "Set default enable_thinking to False",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-23T02:26:16Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "f80041fe728c0cb5147a4aca7e923f4d50a87ce4",
"body": null,
"is_bot": false,
"headline": "Add param to *only* draw from cached annotations",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-23T02:25:42Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "1c9ec1b61372f92b343cfc68129db88f9279ce48",
"body": null,
"is_bot": false,
"headline": "Refactor interpret_neurons.py to work for local LLM",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-23T02:25:23Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "87ea5d87dfc69ebbc7954cf3af902321857ab3bd",
"body": null,
"is_bot": false,
"headline": "Push local experiments for annotation",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-22T17:45:54Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "85ddf5e7d34c5dfb7701f909d98204a6d5e0b76b",
"body": null,
"is_bot": false,
"headline": "Increase gpu util slightly",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-22T17:42:56Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "92d15441a692113dec2280f95e39cf1bc3c1665c",
"body": null,
"is_bot": false,
"headline": "Add bug note",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-22T03:01:07Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "ca391403f5b724e86b580b4011eeeb26021253cf",
"body": "…b to local folder",
"is_bot": false,
"headline": "reset_prefix_cache() before sleeping (not fixing bug); Move testing n…",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-22T02:59:09Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "3b52bf8c5a6592aad9beccf451f1bd3e628ed194",
"body": null,
"is_bot": false,
"headline": "Rename max_new_tokens to max_tokens; allow flexible prompt choice",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-21T22:36:06Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "cc5d62068886f15b9ae515653a81c942090bb24a",
"body": null,
"is_bot": false,
"headline": "Only show tqdm bar for vLLM inference (not for prompt processing)",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-21T22:35:30Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "154d52ec7500a243270c85853faa9b06455c989f",
"body": null,
"is_bot": false,
"headline": "Fix sleeping + lower gpu-util to allow more models in memory",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-21T19:29:08Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "94769635a6e92f928cae7aa9982f2519cba6b51f",
"body": null,
"is_bot": false,
"headline": "Need enable_sleep_mode=True parameter for sleep to actually free memory.",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-21T18:16:16Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "eca27f7116a77862e77f9bc0b63c668cdba5b2c1",
"body": "…ory.",
"is_bot": false,
"headline": "Adding sleep mode functionality, so we can page models on/off GPU mem…",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-21T18:04:53Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "b39990d100626cb5632dbfb59ffc31fc28018832",
"body": null,
"is_bot": false,
"headline": "Update requirements.txt for vLLM",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-21T17:34:38Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "1df65c46fb97d6943498495ad9d92e8ae1f372f1",
"body": null,
"is_bot": false,
"headline": "Simplify testing of local LLMs; assign 0 to missing local annotations",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-21T06:50:59Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "7b4ce9b4a3c51ba48b7230661dd6f29bc449e5a6",
"body": null,
"is_bot": false,
"headline": "Cleanup annotate.py and _local_annotate() function",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-21T05:50:20Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "d2d71587a901d096de9c8d58891b2aa0b09a844a",
"body": null,
"is_bot": false,
"headline": "Make vLLM code more concise: getting completions + model init",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-21T05:26:49Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "0ce45afe794a7257f3d92cad9226bc02ffc8be9f",
"body": null,
"is_bot": false,
"headline": "test qwen3 \"thinking\"",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-11T03:29:48Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "6db71abf9b386dc9bef61a239f4d36059d434a86",
"body": null,
"is_bot": false,
"headline": "Some accuracy results comparing gemma-3-1b-it to gpt-4.1",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-11T03:09:48Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "640fbe420889f92defbaa3adaccf3b68e08f5cc6",
"body": null,
"is_bot": false,
"headline": "batched vLLM - still slow?",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-10T03:32:18Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "514b67bc6abf766fb096abd6cbde7b0506bcf127",
"body": null,
"is_bot": false,
"headline": "add model as explicit parameter to annotation functions",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-10T02:43:35Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "03613ddfb356fd84213cf190f6f8586541db7f5d",
"body": null,
"is_bot": false,
"headline": "add temporary profiling script",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-10T02:11:48Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "c48efbc6c72422bb1e8c7cd4cbab9e98ca5ae20a",
"body": null,
"is_bot": false,
"headline": "fix argument bug - duplicated progress_desc",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-10T02:11:21Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "440291a391c02d74d811ecc5ad9b06568dd070bd",
"body": "…ists on HF before loading.",
"is_bot": false,
"headline": "Tests passing for gemma3 models; fix tqdm progress; check if model ex…",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-08T06:44:12Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "4870e53582e5bb08c9959a4186d5b84de784a71b",
"body": null,
"is_bot": false,
"headline": "Unit tests for local LLMs",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-08T05:22:59Z",
"body_truncated": false,
"is_coding_agent": false
},
{
"oid": "d71c5977742959a7efb62fd2b835cf2b5720df08",
"body": null,
"is_bot": false,
"headline": "Local LLM annotation: Fix pipeline batching / improve performance",
"author_name": "rmovva",
"author_login": "rmovva",
"committed_at": "2025-07-07T23:12:50Z",
"body_truncated": false,
"is_coding_agent": false
}
],
"releases_count": 7,
"commits_last_year": 50,
"latest_release_at": "2026-07-02T18:10:43Z",
"latest_release_tag": "v2.0.1",
"releases_from_tags": true,
"days_since_last_push": 3,
"active_weeks_last_year": 11,
"days_since_latest_release": 24,
"mean_days_between_releases": 72.6
},
"community": {
"has_readme": true,
"has_license": true,
"has_description": true,
"has_contributing": false,
"health_percentage": 42,
"has_issue_template": false,
"has_code_of_conduct": false,
"has_pull_request_template": false
},
"ecosystem": {
"packages": [
{
"name": "hypothesaes",
"exists": true,
"license": null,
"keywords": [
"License :: OSI Approved :: MIT License",
"Operating System :: OS Independent",
"Programming Language :: Python :: 3"
],
"ecosystem": "pypi",
"matches_repo": true,
"registry_url": "https://pypi.org/project/hypothesaes/",
"is_deprecated": false,
"latest_version": "2.0.1",
"repository_url": "https://github.com/rmovva/HypotheSAEs",
"versions_count": 13,
"total_downloads": null,
"dependents_count": null,
"deprecation_note": null,
"maintainers_count": null,
"monthly_downloads": 240,
"first_published_at": "2025-03-16T05:38:41.099368Z",
"latest_published_at": "2026-07-02T18:10:54.071752Z",
"latest_version_yanked": null,
"days_since_latest_publish": 24
}
]
},
"popularity": {
"forks": 28,
"stars": 91,
"watchers": 2,
"fork_history": {
"days": [
{
"date": "2025-04-08",
"count": 1
},
{
"date": "2025-06-08",
"count": 1
},
{
"date": "2025-06-12",
"count": 1
},
{
"date": "2025-07-14",
"count": 1
},
{
"date": "2025-07-22",
"count": 1
},
{
"date": "2025-08-01",
"count": 1
},
{
"date": "2025-08-04",
"count": 1
},
{
"date": "2025-08-09",
"count": 1
},
{
"date": "2025-09-01",
"count": 1
},
{
"date": "2025-09-04",
"count": 1
},
{
"date": "2025-09-06",
"count": 1
},
{
"date": "2025-09-09",
"count": 1
},
{
"date": "2025-09-25",
"count": 1
},
{
"date": "2025-09-29",
"count": 1
},
{
"date": "2025-10-11",
"count": 1
},
{
"date": "2025-10-21",
"count": 1
},
{
"date": "2025-10-25",
"count": 1
},
{
"date": "2025-11-07",
"count": 1
},
{
"date": "2025-11-27",
"count": 1
},
{
"date": "2025-12-21",
"count": 1
},
{
"date": "2026-01-11",
"count": 1
},
{
"date": "2026-01-12",
"count": 1
},
{
"date": "2026-02-02",
"count": 1
},
{
"date": "2026-02-12",
"count": 1
},
{
"date": "2026-05-13",
"count": 1
},
{
"date": "2026-05-31",
"count": 1
},
{
"date": "2026-06-11",
"count": 1
},
{
"date": "2026-07-13",
"count": 1
}
],
"complete": true,
"collected": 28,
"total_forks": 28
},
"star_history": null,
"open_issues_and_prs": 3
},
"ai_readiness": {
"has_nix": false,
"example_dirs": [
"notebooks"
],
"has_llms_txt": false,
"has_dockerfile": false,
"has_mcp_signal": false,
"bootstrap_files": [],
"api_schema_files": [],
"has_devcontainer": false,
"typecheck_configs": [],
"toolchain_manifests": [],
"largest_source_bytes": 21515,
"source_files_sampled": 19,
"oversized_source_files": 0,
"agent_instruction_files": [],
"agent_instruction_max_bytes": null
},
"dependencies": {
"manifests": [
"pyproject.toml",
"requirements.txt"
],
"advisories": {
"error": null,
"scope": "published_package",
"source": "osv",
"findings": [],
"collected": true,
"malicious": [],
"truncated": false,
"by_severity": {},
"advisory_count": 0,
"affected_count": 0,
"assessed_count": 145,
"malicious_count": 0,
"assessed_package": "pypi:hypothesaes@2.0.1",
"unassessed_count": 0,
"direct_affected_count": 0
},
"ecosystems": [
"pypi"
],
"dependencies": [],
"all_dependencies": {
"error": null,
"source": "github-sbom",
"packages": [
{
"name": "accelerate",
"direct": false,
"version": null,
"ecosystem": "pypi"
},
{
"name": "jmespath",
"direct": false,
"version": null,
"ecosystem": "pypi"
},
{
"name": "jupyter",
"direct": false,
"version": null,
"ecosystem": "pypi"
},
{
"name": "matplotlib",
"direct": false,
"version": null,
"ecosystem": "pypi"
},
{
"name": "numpy",
"direct": false,
"version": null,
"ecosystem": "pypi"
},
{
"name": "openai",
"direct": false,
"version": null,
"ecosystem": "pypi"
},
{
"name": "pandas",
"direct": false,
"version": null,
"ecosystem": "pypi"
},
{
"name": "pytest",
"direct": false,
"version": null,
"ecosystem": "pypi"
},
{
"name": "scikit-learn",
"direct": false,
"version": null,
"ecosystem": "pypi"
},
{
"name": "scipy",
"direct": false,
"version": null,
"ecosystem": "pypi"
},
{
"name": "sentence-transformers",
"direct": false,
"version": null,
"ecosystem": "pypi"
},
{
"name": "setuptools",
"direct": false,
"version": null,
"ecosystem": "pypi"
},
{
"name": "statsmodels",
"direct": false,
"version": null,
"ecosystem": "pypi"
},
{
"name": "tiktoken",
"direct": false,
"version": null,
"ecosystem": "pypi"
},
{
"name": "torch",
"direct": false,
"version": null,
"ecosystem": "pypi"
},
{
"name": "tqdm",
"direct": false,
"version": null,
"ecosystem": "pypi"
},
{
"name": "transformers",
"direct": false,
"version": null,
"ecosystem": "pypi"
}
],
"collected": true,
"truncated": false,
"total_count": 17,
"direct_count": 0,
"indirect_count": 17
}
},
"maintainership": {
"issues": {
"open_prs": 2,
"merged_prs": 5,
"open_issues": 1,
"closed_ratio": 0.8,
"closed_issues": 4,
"closed_unmerged_prs": 0
},
"bus_factor": 1,
"bot_contributors": 0,
"top_contributors": [
{
"type": "User",
"login": "rmovva",
"commits": 148,
"avatar_url": "https://avatars.githubusercontent.com/u/17256372?v=4"
},
{
"type": "User",
"login": "Antebe",
"commits": 1,
"avatar_url": "https://avatars.githubusercontent.com/u/54448351?v=4"
},
{
"type": "User",
"login": "adityad2123",
"commits": 1,
"avatar_url": "https://avatars.githubusercontent.com/u/76717200?v=4"
}
],
"contributors_sampled": 3,
"top_contributor_share": 0.987
},
"quality_signals": {
"has_ci": false,
"has_tests": true,
"ci_workflows": [],
"has_docs_dir": false,
"linter_configs": [],
"has_editorconfig": false,
"has_linter_config": false,
"has_precommit_config": false
},
"security_signals": {
"lockfiles": [],
"scorecard": {
"checks": [
{
"name": "Binary-Artifacts",
"score": 10,
"reason": "no binaries found in the repo",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#binary-artifacts"
},
{
"name": "Branch-Protection",
"score": 0,
"reason": "branch protection not enabled on development/release branches",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#branch-protection"
},
{
"name": "CI-Tests",
"score": 0,
"reason": "0 out of 3 merged PRs checked by a CI test -- score normalized to 0",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#ci-tests"
},
{
"name": "CII-Best-Practices",
"score": 0,
"reason": "no effort to earn an OpenSSF best practices badge detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#cii-best-practices"
},
{
"name": "Code-Review",
"score": 0,
"reason": "Found 2/30 approved changesets -- score normalized to 0",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#code-review"
},
{
"name": "Contributors",
"score": 3,
"reason": "project has 1 contributing companies or organizations -- score normalized to 3",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#contributors"
},
{
"name": "Dangerous-Workflow",
"score": null,
"reason": "no workflows found",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#dangerous-workflow"
},
{
"name": "Dependency-Update-Tool",
"score": 0,
"reason": "no update tool detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#dependency-update-tool"
},
{
"name": "Fuzzing",
"score": 0,
"reason": "project is not fuzzed",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#fuzzing"
},
{
"name": "License",
"score": 10,
"reason": "license file detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#license"
},
{
"name": "Maintained",
"score": 3,
"reason": "3 commit(s) and 1 issue activity found in the last 90 days -- score normalized to 3",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#maintained"
},
{
"name": "Packaging",
"score": null,
"reason": "packaging workflow not detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#packaging"
},
{
"name": "Pinned-Dependencies",
"score": null,
"reason": "no dependencies found",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#pinned-dependencies"
},
{
"name": "SAST",
"score": 0,
"reason": "SAST tool is not run on all commits -- score normalized to 0",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#sast"
},
{
"name": "Security-Policy",
"score": 0,
"reason": "security policy file not detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#security-policy"
},
{
"name": "Signed-Releases",
"score": null,
"reason": "no releases found",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#signed-releases"
},
{
"name": "Token-Permissions",
"score": null,
"reason": "No tokens found",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#token-permissions"
},
{
"name": "Vulnerabilities",
"score": 10,
"reason": "0 existing vulnerabilities detected",
"documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#vulnerabilities"
}
],
"commit": "706d8979c71befe8e3151f51a8d4dbf87d4d7e41",
"ran_at": "2026-07-27T13:12:18Z",
"aggregate_score": 2.9,
"scorecard_version": "v5.5.0"
},
"has_codeql_workflow": false,
"has_security_policy": false,
"has_dependabot_config": false
},
"contribution_flow": {
"collected": true,
"ci_last_run_at": "2026-07-24T00:08:28Z",
"oldest_open_prs": [
{
"number": 9,
"created_at": "2025-08-06T23:54:25Z",
"last_comment_at": null,
"last_comment_author": null
},
{
"number": 10,
"created_at": "2026-01-05T16:42:23Z",
"last_comment_at": null,
"last_comment_author": null
}
],
"last_merged_pr_at": "2026-07-24T00:08:27Z",
"ci_last_conclusion": null,
"oldest_open_issues": [
{
"number": 5,
"created_at": "2025-06-14T23:00:24Z",
"last_comment_at": "2026-01-05T16:29:45Z",
"last_comment_author": "Treasure-Mayowa"
}
]
}
},
"config": {
"disabled_metrics": [],
"disabled_categories": [],
"disabled_components": {}
},
"source": {
"url": "https://github.com/rmovva/HypotheSAEs",
"host": "github.com",
"name": "HypotheSAEs",
"owner": "rmovva"
},
"metrics": {
"overall": {
"key": "overall",
"band": "moderate",
"name": "Overall health",
"note": null,
"notes": [],
"value": 53,
"inputs": {
"security": 43,
"vitality": 69,
"community": 45,
"governance": 57,
"engineering": 44
},
"components": []
},
"categories": [
{
"key": "vitality",
"band": "moderate",
"name": "Vitality",
"value": 69,
"weight": 0.22,
"metrics": [
{
"key": "development_activity",
"band": "moderate",
"name": "Development activity",
"note": null,
"notes": [],
"value": 62,
"inputs": {
"commits_last_year": 50,
"human_commit_share": 1,
"days_since_last_push": 3,
"active_weeks_last_year": 11
},
"components": [
{
"key": "push_recency",
"name": "Push recency",
"detail": "last push 3 days ago",
"points": 36,
"status": "met",
"details": [
{
"code": "push_recency",
"params": {
"days": 3
}
}
],
"max_points": 36
},
{
"key": "commit_cadence",
"name": "Commit cadence",
"detail": "11/52 weeks with commits",
"points": 7.6,
"status": "partial",
"details": [
{
"code": "commit_cadence_weeks",
"params": {
"weeks": 11
}
}
],
"max_points": 36
},
{
"key": "commit_volume",
"name": "Commit volume",
"detail": "50 commits in the last year",
"points": 15.3,
"status": "partial",
"details": [
{
"code": "commits_last_year",
"params": {
"count": 50
}
}
],
"max_points": 18
},
{
"key": "openssf_scorecard_maintained",
"name": "OpenSSF Scorecard: Maintained",
"detail": "3 commit(s) and 1 issue activity found in the last 90 days -- score normalized to 3",
"points": 3,
"status": "partial",
"details": [],
"max_points": 10
}
]
},
{
"key": "release_discipline",
"band": "good",
"name": "Release discipline",
"note": "Excluded from scoring (no data or not applicable): OpenSSF Scorecard: Signed-Releases. Remaining weights renormalized.",
"notes": [
{
"code": "excluded_no_data",
"params": {
"components": [
"openssf_scorecard_signed_releases"
]
}
},
{
"code": "weights_renormalized",
"params": {}
}
],
"value": 80,
"inputs": {
"releases_count": 7,
"latest_release_tag": "v2.0.1",
"releases_from_tags": true,
"days_since_latest_release": 24,
"mean_days_between_releases": 72.6
},
"components": [
{
"key": "ships_releases",
"name": "Ships releases",
"detail": "7 version tags (no GitHub releases)",
"points": 16.2,
"status": "partial",
"details": [
{
"code": "version_tags_no_releases",
"params": {
"count": 7
}
}
],
"max_points": 27
},
{
"key": "release_recency",
"name": "Release recency",
"detail": "latest release 24 days ago",
"points": 36,
"status": "met",
"details": [
{
"code": "release_recency",
"params": {
"days": 24
}
}
],
"max_points": 36
},
{
"key": "release_cadence",
"name": "Release cadence",
"detail": "a release every ~72.6 days",
"points": 19.8,
"status": "partial",
"details": [
{
"code": "release_cadence",
"params": {
"gap": 72.6
}
}
],
"max_points": 27
},
{
"key": "openssf_scorecard_signed_releases",
"name": "OpenSSF Scorecard: Signed-Releases",
"detail": "no releases found",
"points": 0,
"status": "excluded",
"details": [
{
"code": "no_data",
"params": {}
}
],
"max_points": 10
}
]
},
{
"key": "abandonment",
"band": "excellent",
"name": "Abandonment",
"note": null,
"notes": [],
"value": 100,
"inputs": {
"cap": null,
"state": "maintained",
"guards": [],
"signals": [],
"red_flag": false,
"multiplier_pct": 100,
"declared_reason": null,
"unverified_reason": null,
"unanswered_open_prs": null,
"unanswered_open_issues": null,
"days_since_last_merged_pr": null,
"days_since_last_human_commit": 3,
"days_since_last_human_commit_is_floor": false
},
"components": [
{
"key": "project_is_still_maintained",
"name": "Project is still maintained",
"detail": "last human commit 3 days ago",
"points": 100,
"status": "met",
"details": [
{
"code": "abandonment_maintained",
"params": {
"days": 3
}
}
],
"max_points": 100
}
]
}
],
"description": "Is the project alive — is code being written and are releases shipping?"
},
{
"key": "community",
"band": "at_risk",
"name": "Community & Adoption",
"value": 45,
"weight": 0.18,
"metrics": [
{
"key": "popularity",
"band": "at_risk",
"name": "Popularity & adoption",
"note": null,
"notes": [],
"value": 44,
"inputs": {
"forks": 28,
"stars": 91,
"watchers": 2,
"growth_state": "unverified",
"growth_factor_pct": 100,
"growth_unverified_reason": "no_history"
},
"components": [
{
"key": "stars",
"name": "Stars",
"detail": "91 stars",
"points": 31.7,
"status": "partial",
"details": [
{
"code": "stars",
"params": {
"count": 91
}
}
],
"max_points": 60
},
{
"key": "forks",
"name": "Forks",
"detail": "28 forks",
"points": 11.9,
"status": "partial",
"details": [
{
"code": "forks",
"params": {
"count": 28
}
}
],
"max_points": 25
},
{
"key": "watchers",
"name": "Watchers",
"detail": "2 watchers",
"points": 0,
"status": "missed",
"details": [
{
"code": "watchers",
"params": {
"count": 2
}
}
],
"max_points": 15
}
]
},
{
"key": "community_health",
"band": "moderate",
"name": "Community health",
"note": null,
"notes": [],
"value": 50,
"inputs": {
"has_readme": true,
"has_license": true,
"has_contributing": false,
"has_issue_template": false,
"has_code_of_conduct": false,
"has_pull_request_template": false
},
"components": [
{
"key": "readme",
"name": "README",
"detail": null,
"points": 22.5,
"status": "met",
"details": [],
"max_points": 22.5
},
{
"key": "license",
"name": "License",
"detail": "recognized license (Apache-2.0)",
"points": 22.5,
"status": "met",
"details": [
{
"code": "license_standard",
"params": {}
},
{
"code": "license_spdx",
"params": {
"spdx": "Apache-2.0"
}
}
],
"max_points": 22.5
},
{
"key": "contributing_guide",
"name": "CONTRIBUTING guide",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 18
},
{
"key": "code_of_conduct",
"name": "Code of conduct",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 13.5
},
{
"key": "issue_template",
"name": "Issue template",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 7.2
},
{
"key": "pr_template",
"name": "PR template",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 6.3
}
]
},
{
"key": "ecosystem_adoption",
"band": "at_risk",
"name": "Ecosystem adoption (downloads)",
"note": "Excluded from scoring (no data or not applicable): Registry dependents. Remaining weights renormalized.",
"notes": [
{
"code": "excluded_no_data",
"params": {
"components": [
"registry_dependents"
]
}
},
{
"code": "weights_renormalized",
"params": {}
}
],
"value": 40,
"inputs": {
"packages": [
"hypothesaes"
],
"dependents": null,
"ecosystems": "pypi",
"total_downloads": null,
"monthly_downloads": 240
},
"components": [
{
"key": "monthly_downloads",
"name": "Monthly downloads",
"detail": "240 downloads/month across pypi",
"points": 31.8,
"status": "partial",
"details": [
{
"code": "downloads_monthly",
"params": {
"count": 240,
"ecosystems": "pypi"
}
}
],
"max_points": 80
},
{
"key": "registry_dependents",
"name": "Registry dependents",
"detail": "not reported by this ecosystem",
"points": 0,
"status": "excluded",
"details": [
{
"code": "not_reported_by_this_ecosystem",
"params": {}
}
],
"max_points": 20
}
]
}
],
"description": "Does the project have users, downloads, attention, and a welcoming setup for contributors?"
},
{
"key": "governance",
"band": "moderate",
"name": "Sustainability & Governance",
"value": 57,
"weight": 0.24,
"metrics": [
{
"key": "maintainer_resilience",
"band": "critical",
"name": "Maintainer resilience (bus factor)",
"note": null,
"notes": [],
"value": 16,
"inputs": {
"bus_factor": 1,
"contributors_sampled": 3,
"top_contributor_share": 0.987
},
"components": [
{
"key": "bus_factor",
"name": "Bus factor",
"detail": "1 contributor(s) cover half of all commits",
"points": 9,
"status": "partial",
"details": [
{
"code": "bus_factor",
"params": {
"count": 1
}
}
],
"max_points": 54
},
{
"key": "commit_distribution",
"name": "Commit distribution",
"detail": "top contributor authored 99% of commits",
"points": 0.3,
"status": "partial",
"details": [
{
"code": "top_contributor_share",
"params": {
"share": 99
}
}
],
"max_points": 22.5
},
{
"key": "contributor_breadth",
"name": "Contributor breadth",
"detail": "3 contributors",
"points": 4.1,
"status": "partial",
"details": [
{
"code": "contributors_sampled",
"params": {
"count": 3
}
}
],
"max_points": 13.5
},
{
"key": "openssf_scorecard_contributors",
"name": "OpenSSF Scorecard: Contributors",
"detail": "project has 1 contributing companies or organizations -- score normalized to 3",
"points": 3,
"status": "partial",
"details": [],
"max_points": 10
}
]
},
{
"key": "responsiveness",
"band": "good",
"name": "Issue & PR responsiveness",
"note": null,
"notes": [],
"value": 76,
"inputs": {
"merged_prs": 5,
"open_issues": 1,
"closed_issues": 4,
"issue_closed_ratio": 0.8,
"closed_unmerged_prs": 0
},
"components": [
{
"key": "issue_resolution",
"name": "Issue resolution",
"detail": "80% of issues closed",
"points": 37.4,
"status": "partial",
"details": [
{
"code": "issues_closed_share",
"params": {
"share": 80
}
}
],
"max_points": 46.75
},
{
"key": "pr_acceptance",
"name": "PR acceptance",
"detail": "5/5 decided PRs merged",
"points": 38.2,
"status": "met",
"details": [
{
"code": "decided_prs_merged",
"params": {
"merged": 5,
"decided": 5
}
}
],
"max_points": 38.25
},
{
"key": "openssf_scorecard_code_review",
"name": "OpenSSF Scorecard: Code-Review",
"detail": "Found 2/30 approved changesets -- score normalized to 0",
"points": 0,
"status": "missed",
"details": [],
"max_points": 15
}
]
},
{
"key": "stewardship",
"band": "moderate",
"name": "Ownership & stewardship",
"note": "Excluded from scoring (no data or not applicable): Verified domain. Remaining weights renormalized.",
"notes": [
{
"code": "excluded_no_data",
"params": {
"components": [
"verified_domain"
]
}
},
{
"code": "weights_renormalized",
"params": {}
}
],
"value": 53,
"inputs": {
"followers": 20,
"owner_type": "User",
"is_verified": null,
"owner_login": "rmovva",
"public_repos": 33,
"account_age_days": 3814
},
"components": [
{
"key": "ownership_backing",
"name": "Ownership backing",
"detail": "personal (user) account",
"points": 10,
"status": "partial",
"details": [
{
"code": "owner_personal",
"params": {}
}
],
"max_points": 30
},
{
"key": "verified_domain",
"name": "Verified domain",
"detail": "not applicable to user accounts",
"points": 0,
"status": "excluded",
"details": [
{
"code": "not_applicable_to_user_accounts",
"params": {}
}
],
"max_points": 20
},
{
"key": "owner_reach",
"name": "Owner reach",
"detail": "20 followers of rmovva",
"points": 9.5,
"status": "partial",
"details": [
{
"code": "owner_followers",
"params": {
"count": 20,
"login": "rmovva"
}
}
],
"max_points": 25
},
{
"key": "track_record",
"name": "Track record",
"detail": "33 public repos, account ~10 yr old",
"points": 23.2,
"status": "partial",
"details": [
{
"code": "public_repos",
"params": {
"count": 33
}
},
{
"code": "account_age_years",
"params": {
"years": 10
}
}
],
"max_points": 25
}
]
},
{
"key": "package_maintenance",
"band": "excellent",
"name": "Package maintenance",
"note": null,
"notes": [],
"value": 100,
"inputs": {
"packages": [
"hypothesaes"
],
"ecosystems": "pypi",
"any_deprecated": false,
"min_days_since_publish": 24
},
"components": [
{
"key": "published_resolvable",
"name": "Published & resolvable",
"detail": "1 package(s) on pypi",
"points": 25,
"status": "met",
"details": [
{
"code": "packages_published",
"params": {
"count": 1,
"ecosystems": "pypi"
}
}
],
"max_points": 25
},
{
"key": "publish_recency",
"name": "Publish recency",
"detail": "latest publish 24 days ago",
"points": 35,
"status": "met",
"details": [
{
"code": "publish_recency",
"params": {
"days": 24
}
}
],
"max_points": 35
},
{
"key": "version_history",
"name": "Version history",
"detail": "13 published versions",
"points": 20,
"status": "met",
"details": [
{
"code": "published_versions",
"params": {
"count": 13
}
}
],
"max_points": 20
},
{
"key": "not_deprecated",
"name": "Not deprecated",
"detail": "active, not deprecated or yanked",
"points": 20,
"status": "met",
"details": [
{
"code": "package_not_deprecated",
"params": {}
}
],
"max_points": 20
}
]
}
],
"description": "Will the project survive its people — bus factor, responsiveness, who backs it, and package upkeep?"
},
{
"key": "engineering",
"band": "at_risk",
"name": "Engineering Quality",
"value": 44,
"weight": 0.2,
"metrics": [
{
"key": "engineering_practices",
"band": "critical",
"name": "Engineering practices",
"note": null,
"notes": [],
"value": 24,
"inputs": {
"has_ci": false,
"has_tests": true,
"has_editorconfig": false,
"has_linter_config": false,
"has_precommit_config": false
},
"components": [
{
"key": "ci_workflows",
"name": "CI workflows",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 24
},
{
"key": "tests_present",
"name": "Tests present",
"detail": null,
"points": 24,
"status": "met",
"details": [],
"max_points": 24
},
{
"key": "linter_config",
"name": "Linter config",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 16
},
{
"key": "pre_commit_hooks",
"name": "Pre-commit hooks",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 9.6
},
{
"key": "editorconfig",
"name": ".editorconfig",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 6.4
},
{
"key": "openssf_scorecard_ci_tests",
"name": "OpenSSF Scorecard: CI-Tests",
"detail": "0 out of 3 merged PRs checked by a CI test -- score normalized to 0",
"points": 0,
"status": "missed",
"details": [],
"max_points": 20
}
]
},
{
"key": "documentation",
"band": "good",
"name": "Documentation",
"note": null,
"notes": [],
"value": 75,
"inputs": {
"topics": [
"ai-for-science",
"computational-social-science",
"interpretability",
"nlp",
"sparse-autoencoders",
"topic-modeling"
],
"has_wiki": true,
"homepage": "https://hypothesaes.org",
"has_readme": true,
"has_docs_dir": false,
"has_description": true
},
"components": [
{
"key": "readme",
"name": "README",
"detail": null,
"points": 30,
"status": "met",
"details": [],
"max_points": 30
},
{
"key": "documentation_directory",
"name": "Documentation directory",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 25
},
{
"key": "documentation_homepage_site",
"name": "Documentation / homepage site",
"detail": "https://hypothesaes.org",
"points": 15,
"status": "met",
"details": [],
"max_points": 15
},
{
"key": "repository_description",
"name": "Repository description",
"detail": null,
"points": 10,
"status": "met",
"details": [],
"max_points": 10
},
{
"key": "topics",
"name": "Topics",
"detail": "6 topics",
"points": 10,
"status": "met",
"details": [
{
"code": "topics_count",
"params": {
"count": 6
}
}
],
"max_points": 10
},
{
"key": "wiki",
"name": "Wiki",
"detail": null,
"points": 10,
"status": "met",
"details": [],
"max_points": 10
}
]
}
],
"description": "Are baseline engineering and documentation practices in place?"
},
{
"key": "security",
"band": "at_risk",
"name": "Security",
"value": 43,
"weight": 0.16,
"metrics": [
{
"key": "security_posture",
"band": "critical",
"name": "Security posture",
"note": "Excluded from scoring (no data or not applicable): Dangerous-Workflow, Packaging, Pinned-Dependencies, Signed-Releases, Token-Permissions. Remaining weights renormalized.",
"notes": [
{
"code": "excluded_no_data",
"params": {
"components": [
"dangerous_workflow",
"packaging",
"pinned_dependencies",
"signed_releases",
"token_permissions"
]
}
},
{
"code": "weights_renormalized",
"params": {}
}
],
"value": 29,
"inputs": {
"source": "openssf_scorecard",
"checks_evaluated": 13,
"scorecard_version": "v5.5.0",
"checks_inconclusive": 5,
"scorecard_aggregate": 2.9
},
"components": [
{
"key": "binary_artifacts",
"name": "Binary-Artifacts",
"detail": "no binaries found in the repo",
"points": 7.5,
"status": "met",
"details": [],
"max_points": 7.5
},
{
"key": "branch_protection",
"name": "Branch-Protection",
"detail": "branch protection not enabled on development/release branches",
"points": 0,
"status": "missed",
"details": [],
"max_points": 7.5
},
{
"key": "ci_tests",
"name": "CI-Tests",
"detail": "0 out of 3 merged PRs checked by a CI test -- score normalized to 0",
"points": 0,
"status": "missed",
"details": [],
"max_points": 2.5
},
{
"key": "cii_best_practices",
"name": "CII-Best-Practices",
"detail": "no effort to earn an OpenSSF best practices badge detected",
"points": 0,
"status": "missed",
"details": [],
"max_points": 2.5
},
{
"key": "code_review",
"name": "Code-Review",
"detail": "Found 2/30 approved changesets -- score normalized to 0",
"points": 0,
"status": "missed",
"details": [],
"max_points": 7.5
},
{
"key": "contributors",
"name": "Contributors",
"detail": "project has 1 contributing companies or organizations -- score normalized to 3",
"points": 0.8,
"status": "partial",
"details": [],
"max_points": 2.5
},
{
"key": "dangerous_workflow",
"name": "Dangerous-Workflow",
"detail": "no workflows found",
"points": 0,
"status": "excluded",
"details": [
{
"code": "no_data",
"params": {}
}
],
"max_points": 10
},
{
"key": "dependency_update_tool",
"name": "Dependency-Update-Tool",
"detail": "no update tool detected",
"points": 0,
"status": "missed",
"details": [],
"max_points": 7.5
},
{
"key": "fuzzing",
"name": "Fuzzing",
"detail": "project is not fuzzed",
"points": 0,
"status": "missed",
"details": [],
"max_points": 5
},
{
"key": "license",
"name": "License",
"detail": "license file detected",
"points": 2.5,
"status": "met",
"details": [],
"max_points": 2.5
},
{
"key": "maintained",
"name": "Maintained",
"detail": "3 commit(s) and 1 issue activity found in the last 90 days -- score normalized to 3",
"points": 2.2,
"status": "partial",
"details": [],
"max_points": 7.5
},
{
"key": "packaging",
"name": "Packaging",
"detail": "packaging workflow not detected",
"points": 0,
"status": "excluded",
"details": [
{
"code": "no_data",
"params": {}
}
],
"max_points": 5
},
{
"key": "pinned_dependencies",
"name": "Pinned-Dependencies",
"detail": "no dependencies found",
"points": 0,
"status": "excluded",
"details": [
{
"code": "no_data",
"params": {}
}
],
"max_points": 5
},
{
"key": "sast",
"name": "SAST",
"detail": "SAST tool is not run on all commits -- score normalized to 0",
"points": 0,
"status": "missed",
"details": [],
"max_points": 5
},
{
"key": "security_policy",
"name": "Security-Policy",
"detail": "security policy file not detected",
"points": 0,
"status": "missed",
"details": [],
"max_points": 5
},
{
"key": "signed_releases",
"name": "Signed-Releases",
"detail": "no releases found",
"points": 0,
"status": "excluded",
"details": [
{
"code": "no_data",
"params": {}
}
],
"max_points": 7.5
},
{
"key": "token_permissions",
"name": "Token-Permissions",
"detail": "No tokens found",
"points": 0,
"status": "excluded",
"details": [
{
"code": "no_data",
"params": {}
}
],
"max_points": 7.5
},
{
"key": "vulnerabilities",
"name": "Vulnerabilities",
"detail": "0 existing vulnerabilities detected",
"points": 7.5,
"status": "met",
"details": [],
"max_points": 7.5
}
]
},
{
"key": "dependency_advisories",
"band": "excellent",
"name": "Dependency advisories",
"note": "Excluded from scoring (no data or not applicable): No advisories left outstanding. Remaining weights renormalized. Matched the pypi:hypothesaes@2.0.1 runtime dependency closure — what installing the published package pulls in — 145 packages. Reachability is not analyzed.",
"notes": [
{
"code": "excluded_no_data",
"params": {
"components": [
"no_advisories_left_outstanding"
]
}
},
{
"code": "weights_renormalized",
"params": {}
},
{
"code": "advisories_scope_published",
"params": {
"package": "pypi:hypothesaes@2.0.1",
"assessed": 145
}
},
{
"code": "advisories_reachability",
"params": {}
}
],
"value": 100,
"inputs": {
"source": "osv",
"advisories": 0,
"affected_packages": 0,
"assessed_packages": 145,
"unassessed_packages": 0,
"affected_by_severity": "none",
"direct_affected_packages": 0
},
"components": [
{
"key": "direct_dependencies_free_of_known_advisories",
"name": "Direct dependencies free of known advisories",
"detail": "no direct dependency carries a known advisory",
"points": 35,
"status": "met",
"details": [
{
"code": "no_direct_advisories",
"params": {}
}
],
"max_points": 35
},
{
"key": "indirect_dependencies_free_of_known_advisories",
"name": "Indirect dependencies free of known advisories",
"detail": "no indirect dependency carries a known advisory",
"points": 25,
"status": "met",
"details": [
{
"code": "no_indirect_advisories",
"params": {}
}
],
"max_points": 25
},
{
"key": "no_advisories_left_outstanding",
"name": "No advisories left outstanding",
"detail": "no advisory carries a publication date",
"points": 0,
"status": "excluded",
"details": [
{
"code": "advisories_no_publication_date",
"params": {}
}
],
"max_points": 40
}
]
},
{
"key": "malicious_dependencies",
"band": "excellent",
"name": "Malicious dependencies",
"note": null,
"notes": [],
"value": 100,
"inputs": {
"source": "osv",
"meaning": "reported as a malicious package by the OpenSSF corpus; the remedy is removal or moving off the compromised name, never an upgrade of the same artifact. Versions the registry has since pulled are listed but not scored",
"packages": [],
"red_flag": false,
"assessed_packages": 145,
"malicious_packages": 0,
"direct_malicious_packages": 0,
"withdrawn_malicious_packages": 0,
"installable_malicious_packages": 0
},
"components": [
{
"key": "no_dependency_reported_as_a_malicious_package",
"name": "No dependency reported as a malicious package",
"detail": "no dependency is reported as a malicious package",
"points": 100,
"status": "met",
"details": [
{
"code": "no_malicious_dependencies",
"params": {}
}
],
"max_points": 100
}
]
}
],
"description": "Are visible security and supply-chain practices strong, with no malicious dependency and no unresolved high-risk jurisdiction exposure?"
},
{
"key": "ai_readiness",
"band": "critical",
"name": "AI Readiness",
"value": 24,
"weight": 0,
"metrics": [
{
"key": "ai_agent_context",
"band": "critical",
"name": "Agent context & guidance",
"note": null,
"notes": [],
"value": 2,
"inputs": {
"has_llms_txt": false,
"legible_history_share": 0.04,
"agent_instruction_files": [],
"agent_instruction_max_bytes": null
},
"components": [
{
"key": "agent_instructions",
"name": "Agent instructions",
"detail": "no CLAUDE.md / AGENTS.md / editor rules",
"points": 0,
"status": "missed",
"details": [
{
"code": "no_agent_instructions",
"params": {}
}
],
"max_points": 45
},
{
"key": "machine_readable_docs_llms_txt",
"name": "Machine-readable docs (llms.txt)",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 15
},
{
"key": "legible_commit_history",
"name": "Legible commit history",
"detail": "4 of 100 human commits state their intent (structured subject or explanatory body)",
"points": 2.1,
"status": "partial",
"details": [
{
"code": "legible_history",
"params": {
"legible": 4,
"sampled": 100
}
}
],
"max_points": 40
}
]
},
{
"key": "ai_verify_loop",
"band": "critical",
"name": "Verify loop (build / test / typecheck)",
"note": "Excluded from scoring (no data or not applicable): OpenSSF Scorecard: Pinned-Dependencies. Remaining weights renormalized.",
"notes": [
{
"code": "excluded_no_data",
"params": {
"components": [
"openssf_scorecard_pinned_dependencies"
]
}
},
{
"code": "weights_renormalized",
"params": {}
}
],
"value": 24,
"inputs": {
"has_nix": false,
"has_tests": true,
"lockfiles": [],
"has_dockerfile": false,
"typed_language": false,
"bootstrap_files": [],
"has_devcontainer": false,
"has_linter_config": false,
"typecheck_configs": [],
"agent_commit_share": 0,
"toolchain_manifests": [],
"dependency_bot_commit_share": 0
},
"components": [
{
"key": "one_command_bootstrap",
"name": "One-command bootstrap",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 18
},
{
"key": "automated_tests",
"name": "Automated tests",
"detail": null,
"points": 22,
"status": "met",
"details": [],
"max_points": 22
},
{
"key": "lint_format_config",
"name": "Lint / format config",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 11
},
{
"key": "static_type_checking",
"name": "Static type checking",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 11
},
{
"key": "reproducible_environment",
"name": "Reproducible environment",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 10
},
{
"key": "demonstrated_agent_practice",
"name": "Demonstrated agent practice",
"detail": "no agent-authored commits among the last 100",
"points": 0,
"status": "missed",
"details": [
{
"code": "no_agent_authored_commits",
"params": {
"sampled": 100
}
}
],
"max_points": 10
},
{
"key": "automated_maintenance",
"name": "Automated maintenance",
"detail": "no automated dependency updates observed",
"points": 0,
"status": "missed",
"details": [
{
"code": "no_dependency_automation",
"params": {}
}
],
"max_points": 8
},
{
"key": "openssf_scorecard_pinned_dependencies",
"name": "OpenSSF Scorecard: Pinned-Dependencies",
"detail": "no dependencies found",
"points": 0,
"status": "excluded",
"details": [
{
"code": "no_data",
"params": {}
}
],
"max_points": 10
}
]
},
{
"key": "ai_code_legibility",
"band": "moderate",
"name": "Code legibility for models",
"note": null,
"notes": [],
"value": 55,
"inputs": {
"primary_language": "Jupyter Notebook",
"largest_source_bytes": 21515,
"source_files_sampled": 19,
"oversized_source_files": 0
},
"components": [
{
"key": "type_checkable_code",
"name": "Type-checkable code",
"detail": "Jupyter Notebook without a type-check config",
"points": 0,
"status": "missed",
"details": [
{
"code": "no_typecheck_config_language",
"params": {
"language": "Jupyter Notebook"
}
}
],
"max_points": 45
},
{
"key": "manageable_file_sizes",
"name": "Manageable file sizes",
"detail": "0/19 source files over 60KB",
"points": 55,
"status": "met",
"details": [
{
"code": "oversized_source_files",
"params": {
"kb": 60,
"sampled": 19,
"oversized": 0
}
}
],
"max_points": 55
}
]
},
{
"key": "ai_interfaces",
"band": "at_risk",
"name": "Machine-readable interfaces",
"note": null,
"notes": [],
"value": 40,
"inputs": {
"example_dirs": [
"notebooks"
],
"has_mcp_signal": false,
"api_schema_files": []
},
"components": [
{
"key": "api_schema_openapi_graphql_proto",
"name": "API schema (OpenAPI/GraphQL/proto)",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 40
},
{
"key": "mcp_server",
"name": "MCP server",
"detail": null,
"points": 0,
"status": "missed",
"details": [],
"max_points": 20
},
{
"key": "runnable_examples",
"name": "Runnable examples",
"detail": "notebooks",
"points": 40,
"status": "met",
"details": [
{
"code": "file_list",
"params": {
"files": "notebooks"
}
}
],
"max_points": 40
}
]
}
],
"description": "How well is the repo equipped to be developed and maintained with AI coding agents? An independent, experimental badge — weight 0.0, so it is surfaced on its own and does not affect the overall health score."
}
],
"metrics_version": "1.13.0"
},
"warnings": [
"Star history unavailable: GitHub GraphQL error: Resource not accessible by personal access token"
],
"report_type": "repository",
"generated_at": "2026-07-27T13:12:30.788867Z",
"schema_version": "0.27.0",
"badge_url": "https://raw.githubusercontent.com/inspect-software/badges/main/v1/r/rmovva/HypotheSAEs.svg",
"full_name": "rmovva/HypotheSAEs",
"license_state": "standard",
"license_spdx": "Apache-2.0"
}Scores are signals, not warranties. They reflect publicly visible practices on GitHub — not a code audit, and not a security guarantee.
Missing data is excluded and weights renormalized, never scored as zero. Methodology is versioned and open: metrics v1.13.0, schema v0.27.0 — full methodology · metrics wiki.
How one result sits in the wider record: aggregate statistics — PyPI.