Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 94961
    Prev
    Next
    INDEX
    Explanations

    gender stereotypes

    np_max-act · gemini-2.0-flash

    discussions of gender roles and stereotypes, especially societal expectations distinguishing boys and girls or men and women.

    oai_token-act-pair · gpt-5Triggered by @tatsatx
    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
    _missing
    -0.08
     substring
    -0.08
     procesa
    -0.08
    -0.07
     основания
    -0.07
    artz
    -0.07
    黎
    -0.07
    wall
    -0.07
    ighbors
    -0.07
    missing
    -0.07
    POSITIVE LOGITS
     stereotyp
    0.10
    .RO
    0.09
     swapped
    0.09
     റോ
    0.09
     heterosexual
    0.09
     roteiro
    0.09
     hybr
    0.08
     societal
    0.08
     perceived
    0.08
     hed
    0.08
    Activations Density 0.019%

    No Known Activations