© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 47922
    Prev
    Next
    INDEX
    Explanations

    datapack

    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
     Saddle
    -0.08
     saddle
    -0.08
     electroly
    -0.08
     CEO
    -0.07
     funda
    -0.07
     Connie
    -0.07
    (Unmanaged
    -0.07
     CFO
    -0.07
    
    -0.07
    _pid
    -0.07
    POSITIVE LOGITS
     권
    0.08
    .override
    0.08
     बन
    0.08
     amber
    0.08
     ^^↵↵
    0.08
     만들
    0.07
    권
    0.07
     artisan
    0.07
     조
    0.07
    aking
    0.07
    Activations Density 0.001%

    No Known Activations