© 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. 3-RESID-POST-AA
    11. 12951
    Prev
    Next
    INDEX
    Explanations

    kinds

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propensity
    -0.08
     Rui
    -0.07
     seg
    -0.07
     supervised
    -0.07
    (rad
    -0.07
     coached
    -0.07
     Audible
    -0.07
    871
    -0.07
    prog
    -0.07
    feet
    -0.07
    POSITIVE LOGITS
    Spot
    0.09
    heli
    0.08
    spot
    0.08
     treffen
    0.08
     XElement
    0.07
    �
    0.07
     spills
    0.07
    留
    0.07
    زی
    0.07
     व्यव
    0.07
    Activations Density 0.014%

    No Known Activations