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

    Neuronpedia

    APICircuit 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. 15-RESID-POST-AA
    6. 0
    Prev
    Next
    INDEX
    Explanations

    semicolon

    np_max-act-logits · gemini-2.0-flash

    system or metadata tokens and XML/special formatting markers.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @kdearsty
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     באמצ
    -0.09
     Coch
    -0.08
     Priority
    -0.08
     Medium
    -0.08
     Commit
    -0.08
    323
    -0.08
     Commitment
    -0.08
     Serial
    -0.08
     Mis
    -0.08
     Comfort
    -0.08
    POSITIVE LOGITS
    маган
    0.08
     quantify
    0.08
    纸
    0.08
    ித்து
    0.08
     sharpen
    0.08
     şi
    0.08
    urban
    0.08
     extraordinarily
    0.08
    subtract
    0.08
     outrageous
    0.08
    Activations Density 0.000%

    No Known Activations