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

    Neuronpedia

    APICircuit 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. 12997
    Prev
    Next
    INDEX
    Explanations

    weigh

    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
    'appr
    -0.08
     vooruit
    -0.08
    chen
    -0.08
     حقي
    -0.07
    uwe
    -0.07
    Hdr
    -0.07
    -human
    -0.07
    //
    -0.07
     double
    -0.07
    稳定
    -0.07
    POSITIVE LOGITS
     гур
    0.09
     gutters
    0.09
     дерева
    0.08
    parks
    0.08
     piz
    0.08
     чаш
    0.08
     electricians
    0.08
     вопросов
    0.08
     plumbers
    0.08
     baff
    0.08
    Activations Density 0.002%

    No Known Activations