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. 88246
    Prev
    Next
    INDEX
    Explanations

    Legal documents/acts

    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
    mě
    -0.08
    .debug
    -0.08
    Debug
    -0.08
    .Debug
    -0.08
    しい
    -0.08
    ಿಸ್ತ
    -0.08
     carreras
    -0.07
    Slope
    -0.07
     recursive
    -0.07
    忙
    -0.07
    POSITIVE LOGITS
     annul
    0.09
    uments
    0.08
     documentos
    0.08
     dc
    0.08
     mág
    0.08
     mills
    0.08
     Dell
    0.08
     రూప
    0.08
     seals
    0.08
     AML
    0.08
    Activations Density 0.013%

    No Known Activations