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. 15-RESID-POST-AA
    6. 19331
    Prev
    Next
    INDEX
    Explanations

    quotation mark

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Boxes
    -0.09
     ליד
    -0.08
    _Line
    -0.08
    &p
    -0.08
    Caja
    -0.08
    Stmt
    -0.08
    Box
    -0.08
    Saldo
    -0.08
     linea
    -0.08
    Cast
    -0.08
    POSITIVE LOGITS
     certain
    0.08
     конферен
    0.08
     чемпион
    0.08
     сор
    0.08
     главное
    0.08
    нуть
    0.07
     вход
    0.07
     konfer
    0.07
     může
    0.07
     jewel
    0.07
    Activations Density 0.003%

    No Known Activations