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. 56065
    Prev
    Next
    INDEX
    Explanations

    entrepreneurial designs on mugs

    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
     encompass
    -0.09
     eus
    -0.08
     epile
    -0.08
     aku
    -0.08
     bay
    -0.07
     dereg
    -0.07
     hent
    -0.07
     lur
    -0.07
     reka
    -0.07
     encompasses
    -0.07
    POSITIVE LOGITS
     sayesinde
    0.09
    mill
    0.08
     Благодаря
    0.08
     cups
    0.08
    Введите
    0.08
    .Invoke
    0.08
    innon
    0.07
    .Asp
    0.07
     применяется
    0.07
    izado
    0.07
    Activations Density 0.088%

    No Known Activations