© 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. 78406
    Prev
    Next
    INDEX
    Explanations

    Circe and the Odyssey

    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
     trac
    -0.08
     tracer
    -0.08
     hoops
    -0.08
     Feuerwehr
    -0.07
     kier
    -0.07
     przeb
    -0.07
     Trace
    -0.07
     tracing
    -0.07
    维修
    -0.07
    Tracing
    -0.07
    POSITIVE LOGITS
     превращ
    0.09
    ські
    0.08
     hostile
    0.08
     scholarly
    0.08
    CHR
    0.08
    imd
    0.08
     statute
    0.07
    óttir
    0.07
    ')),
    0.07
    servez
    0.07
    Activations Density 0.000%

    No Known Activations