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. 45166
    Prev
    Next
    INDEX
    Explanations

    federal

    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
     Perman
    -0.09
     wash
    -0.07
     Aston
    -0.07
     elong
    -0.07
     bann
    -0.07
     elongated
    -0.07
     Antoine
    -0.07
    orear
    -0.07
    Carn
    -0.07
    essori
    -0.07
    POSITIVE LOGITS
     Affairs
    0.08
    -sponsored
    0.08
    -owned
    0.08
    -funded
    0.08
     conspiracy
    0.08
     konse
    0.08
     affairs
    0.08
    .policy
    0.08
     Interstate
    0.07
     skr
    0.07
    Activations Density 0.011%

    No Known Activations