© 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. 78447
    Prev
    Next
    INDEX
    Explanations

    T

    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
    iex
    -0.08
     dage
    -0.08
     експ
    -0.08
    inga
    -0.08
    inki
    -0.07
    $new
    -0.07
    -0.07
     ekspl
    -0.07
     <$
    -0.07
     bg
    -0.07
    POSITIVE LOGITS
    Fast
    0.08
     Fast
    0.08
     Duplex
    0.08
    Notify
    0.08
    .embedding
    0.07
     زخ
    0.07
    Checker
    0.07
     couvre
    0.07
    chor
    0.07
     Sav
    0.07
    Activations Density 0.002%
    No Known Activations