© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 25106
    Prev
    Next
    INDEX
    Explanations

    marginalized groups

    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
     declare
    -0.08
     lebt
    -0.08
     capsule
    -0.08
    /pro
    -0.08
    猛烈
    -0.07
    (add
    -0.07
    /man
    -0.07
    隆
    -0.07
    _adc
    -0.07
    declare
    -0.07
    POSITIVE LOGITS
     racist
    0.10
     interracial
    0.10
     racism
    0.09
     sexist
    0.08
     Exotic
    0.08
     multicultural
    0.08
     heterosexual
    0.08
     kosher
    0.08
    ileg
    0.08
     minst
    0.08
    Activations Density 0.172%

    No Known Activations