© 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. 656
    Prev
    Next
    INDEX
    Explanations

    magnetic

    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
     prescribing
    -0.08
     consisted
    -0.08
     sext
    -0.08
     comprised
    -0.08
     cols
    -0.08
    Emergency
    -0.08
     flames
    -0.08
    ناس
    -0.08
     parentheses
    -0.07
    FED
    -0.07
    POSITIVE LOGITS
    anch
    0.08
     orphan
    0.08
    प्प
    0.07
     anchored
    0.07
    .thread
    0.07
     RNA
    0.07
     Diario
    0.07
     قرب
    0.07
    วม
    0.07
     प्लेट
    0.07
    Activations Density 0.002%

    No Known Activations