© 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. 95226
    Prev
    Next
    INDEX
    Explanations

    sun

    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
    MISSIONS
    -0.08
     estím
    -0.08
    instruction
    -0.08
    overe
    -0.08
    贴
    -0.08
     Fisk
    -0.07
    μά
    -0.07
     ستكون
    -0.07
     gue
    -0.07
    adeen
    -0.07
    POSITIVE LOGITS
     tighten
    0.08
    akh
    0.08
    र्ड
    0.08
    요일
    0.08
     भारतीय
    0.07
     oddly
    0.07
    0.07
     skies
    0.07
     Odisha
    0.07
     varn
    0.07
    Activations Density 0.065%

    No Known Activations