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. 8413
    Prev
    Next
    INDEX
    Explanations

    Math reasoning

    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
    Laura
    -0.08
    soy
    -0.08
    Libre
    -0.08
     donc
    -0.07
     ғылым
    -0.07
     дүйн
    -0.07
    atea
    -0.07
     prends
    -0.07
     sada
    -0.07
     дүни
    -0.07
    POSITIVE LOGITS
    pc
    0.08
     thì
    0.08
     one's
    0.07
    bill
    0.07
     bust
    0.07
     pc
    0.07
    siblings
    0.07
     كه
    0.07
    053
    0.07
    758
    0.07
    Activations Density 0.211%

    No Known Activations