© 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. 78286
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     monopol
    -0.07
     {*}
    -0.07
    410
    -0.07
     Stock
    -0.07
    .catalog
    -0.07
     Catalog
    -0.07
    cac
    -0.07
     prest
    -0.07
    ά
    -0.07
     ambassadors
    -0.07
    POSITIVE LOGITS
    ，因为
    0.09
    otho
    0.08
    lán
    0.08
    langan
    0.08
     :)↵↵
    0.08
     cộng
    0.08
    plo
    0.08
     hong
    0.08
    יטת
    0.08
    loze
    0.08
    Activations Density 0.095%

    No Known Activations