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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 43564
    Prev
    Next
    INDEX
    Explanations

    import

    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
     midday
    -0.07
    UMP
    -0.07
    polit
    -0.07
     Sawyer
    -0.07
     durumda
    -0.07
     SCI
    -0.07
    kend
    -0.07
     Shane
    -0.07
    вед
    -0.07
    情况下
    -0.07
    POSITIVE LOGITS
     باز
    0.08
     encaps
    0.08
     Codable
    0.08
     Injectable
    0.08
    0.08
     تاک
    0.08
     كيف
    0.08
     trả
    0.08
     මේ
    0.08
     반환
    0.08
    Activations Density 0.009%
    No Known Activations