© 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. 99210
    Prev
    Next
    INDEX
    Explanations

    behind the scenes

    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
    APTER
    -0.07
     Mini
    -0.07
    iton
    -0.07
    ства
    -0.07
    .Bool
    -0.07
    SError
    -0.07
    alz
    -0.07
     खराब
    -0.07
    ിഎ
    -0.07
     doubtful
    -0.07
    POSITIVE LOGITS
     quietly
    0.10
     waits
    0.08
     silently
    0.08
     unseen
    0.08
    -essential
    0.08
    シャ
    0.08
    力量
    0.08
    幕后
    0.08
     पर्द
    0.08
     ход
    0.08
    Activations Density 0.023%

    No Known Activations