Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 44018
    Prev
    Next
    INDEX
    Explanations

    provide

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Deviation
    -0.09
    operand
    -0.09
    rollback
    -0.09
    Inspector
    -0.09
    Undo
    -0.08
    Replay
    -0.08
    commit
    -0.08
    undo
    -0.08
     rup
    -0.08
    Rollback
    -0.08
    POSITIVE LOGITS
     검색
    0.12
     curated
    0.12
    搜尋
    0.12
    搜索
    0.12
     Craigslist
    0.12
     searches
    0.12
    検索
    0.12
     referrals
    0.12
     搜
    0.11
    _urls
    0.11
    Activations Density 0.075%

    No Known Activations