© 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. 47937
    Prev
    Next
    INDEX
    Explanations

    px

    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
    pares
    -0.09
     обор
    -0.09
    uelva
    -0.08
     período
    -0.08
     ";"
    -0.08
     auff
    -0.08
     períodos
    -0.08
     период
    -0.08
     tutk
    -0.08
     unfavorable
    -0.08
    POSITIVE LOGITS
     concr
    0.08
     scratched
    0.08
     stainless
    0.08
     blessures
    0.08
     drinks
    0.08
     UITable
    0.08
     onwards
    0.07
     bounce
    0.07
     جام
    0.07
    /view
    0.07
    Activations Density 0.000%

    No Known Activations