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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RESID-POST-AA
    6. 112963
    Prev
    Next
    INDEX
    Explanations

    ophy

    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
     analyzing
    -0.07
     galvan
    -0.07
     Swagger
    -0.07
    wipe
    -0.07
     Margaret
    -0.07
    .Back
    -0.07
    ğine
    -0.07
    ssh
    -0.07
    _track
    -0.07
     меня
    -0.07
    POSITIVE LOGITS
     天天
    0.08
     inventions
    0.08
     centuries
    0.08
    /forms
    0.08
     बनने
    0.08
     fatto
    0.08
     civilian
    0.07
     restaurant
    0.07
    יצ
    0.07
    cnn
    0.07
    Activations Density 0.000%

    No Known Activations