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. 112964
    Prev
    Next
    INDEX
    Explanations

    Math equations

    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
    _curve
    -0.08
    細
    -0.08
     unnoticed
    -0.07
     Wrangler
    -0.07
    -kar
    -0.07
    .apple
    -0.07
    Tour
    -0.07
     palīdz
    -0.07
     cellul
    -0.07
    甸
    -0.07
    POSITIVE LOGITS
     ум
    0.08
     prefixes
    0.08
     eint
    0.08
     purified
    0.08
    essaa
    0.07
     ಬ್ಯಾಂ
    0.07
    wohn
    0.07
     ബാധ
    0.07
    ällig
    0.07
     Prüf
    0.07
    Activations Density 0.043%

    No Known Activations