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. 90220
    Prev
    Next
    INDEX
    Explanations

    resources

    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
     judiciaire
    -0.08
     dodge
    -0.08
     ciment
    -0.07
     uncl
    -0.07
     gebouwd
    -0.07
     iff
    -0.07
     chirurg
    -0.07
    valuator
    -0.07
    carry
    -0.07
     alfa
    -0.07
    POSITIVE LOGITS
     logos
    0.08
    模板
    0.08
    テン
    0.08
     templates
    0.08
    قراء
    0.08
     goodness
    0.08
    sqlite
    0.08
    语
    0.08
     espí
    0.08
    (template
    0.07
    Activations Density 0.003%

    No Known Activations