© 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. 31052
    Prev
    Next
    INDEX
    Explanations

    product specifications

    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
     posit
    -0.08
    Normalization
    -0.08
     связан
    -0.07
     sagt
    -0.07
    pw
    -0.07
    ناصر
    -0.07
     suw
    -0.07
    ическим
    -0.07
     temps
    -0.07
    աջ
    -0.07
    POSITIVE LOGITS
    ']}↵
    0.08
    IE
    0.08
    geen
    0.08
     stimulation
    0.08
     Oce
    0.08
    0.08
     Oscar
    0.08
    0.07
     Monsters
    0.07
    ;↵↵↵//
    0.07
    Activations Density 0.028%
    No Known Activations