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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 75258
    Prev
    Next
    INDEX
    Explanations

    math

    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
    Hotels
    -0.08
     trailers
    -0.08
     katanya
    -0.08
     Medicare
    -0.08
    .consumer
    -0.08
     Leia
    -0.08
    /banner
    -0.07
     ವೇಳೆ
    -0.07
     Anatom
    -0.07
     Lor
    -0.07
    POSITIVE LOGITS
     textbooks
    0.09
     collegiate
    0.08
     colleg
    0.08
     GCSE
    0.08
     prec
    0.08
     university
    0.08
     undergraduate
    0.08
     क्लब
    0.08
    交流
    0.08
     club
    0.07
    Activations Density 0.005%

    No Known Activations