© 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. 65050
    Prev
    Next
    INDEX
    Explanations

    on

    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
     arac
    -0.09
     diverg
    -0.08
     (
    -0.07
    류
    -0.07
     divergence
    -0.07
     exhaust
    -0.07
    wen
    -0.07
    низ
    -0.07
     OR
    -0.07
     Diver
    -0.06
    POSITIVE LOGITS
    进去
    0.12
    参与
    0.11
    伙伴
    0.11
     beteiligt
    0.11
     enthousiasme
    0.10
     entusiasmo
    0.10
     involvement
    0.10
     mukaan
    0.10
    volved
    0.10
     betrokken
    0.10
    Activations Density 0.111%

    No Known Activations