© 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. 95330
    Prev
    Next
    INDEX
    Explanations

    Stark

    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
     dä
    -0.08
     dn
    -0.08
    umsum
    -0.08
     glaze
    -0.08
     stup
    -0.08
     Tosc
    -0.08
    ropped
    -0.08
     inhale
    -0.08
    etan
    -0.08
    aufnahme
    -0.08
    POSITIVE LOGITS
     Northampton
    0.08
     보내
    0.08
     repairing
    0.08
     tale
    0.07
    iangle
    0.07
     ام
    0.07
     loyal
    0.07
     tide
    0.07
     ל
    0.07
     woodland
    0.07
    Activations Density 0.003%

    No Known Activations