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. 76036
    Prev
    Next
    INDEX
    Explanations

    1

    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
    ({
    ↵
    -0.09
    대로
    -0.08
     inclination
    -0.08
    Incl
    -0.08
    .Matcher
    -0.07
    ({↵
    -0.07
    _func
    -0.07
     betrekking
    -0.07
    worth
    -0.07
    Oder
    -0.07
    POSITIVE LOGITS
    াংল
    0.08
    აწყ
    0.08
    roveň
    0.08
     Zorg
    0.08
    ,:,:
    0.08
    xs
    0.08
    ాఖ్య
    0.08
    াঝ
    0.08
     subsidiaries
    0.08
     Sears
    0.08
    Activations Density 0.002%

    No Known Activations