© 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. 75496
    Prev
    Next
    INDEX
    Explanations

    indicate

    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
    clipse
    -0.07
     stagn
    -0.07
    Ctr
    -0.07
     Rush
    -0.07
    币
    -0.07
    <n
    -0.07
    ecur
    -0.07
    GM
    -0.07
    ก่อน
    -0.06
    aque
    -0.06
    POSITIVE LOGITS
     faptul
    0.09
     Pav
    0.08
     bahwa
    0.08
     возможности
    0.08
     pav
    0.08
     Ane
    0.08
     calves
    0.07
    0.07
    toe
    0.07
     HAS
    0.07
    Activations Density 0.017%
    No Known Activations