© 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. 45250
    Prev
    Next
    INDEX
    Explanations

    derivative

    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
     forecasts
    -0.08
     delivery
    -0.08
     seeds
    -0.07
    bar
    -0.07
     index
    -0.07
     benchmarks
    -0.07
    Bar
    -0.07
     socialist
    -0.07
    ター
    -0.07
     targets
    -0.07
    POSITIVE LOGITS
     사고
    0.09
     רע
    0.08
    .Listener
    0.08
     נוספים
    0.08
     мегӯ
    0.08
     कैम
    0.08
     намай
    0.08
     მეც
    0.08
    湖
    0.08
     นาที
    0.08
    Activations Density 0.013%

    No Known Activations