© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 78976
    Prev
    Next
    INDEX
    Explanations

    laws

    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
     effortless
    -0.10
     Celebrity
    -0.09
     raining
    -0.09
     مشکل
    -0.09
     کیلئے
    -0.08
     Technique
    -0.08
     leisurely
    -0.08
     Oprah
    -0.08
     Fibonacci
    -0.08
     taps
    -0.08
    POSITIVE LOGITS
     statutes
    0.15
     regulations
    0.13
    规定
    0.13
     कानून
    0.13
     amendments
    0.13
    法规
    0.12
     governing
    0.12
     provisions
    0.12
     statutory
    0.12
     legislation
    0.12
    Activations Density 0.079%

    No Known Activations