© 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. 108185
    Prev
    Next
    INDEX
    Explanations

    Mexican culture

    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
    英国
    -0.09
     britannique
    -0.09
     beispielsweise
    -0.09
     примеру
    -0.08
    (())↵
    -0.08
    万元
    -0.08
     überlegen
    -0.08
     thumbs
    -0.08
     anglais
    -0.08
    董
    -0.08
    POSITIVE LOGITS
     Veracruz
    0.13
     Mexico
    0.13
     Colombian
    0.13
     Instituto
    0.13
     México
    0.13
    Mexico
    0.13
     Oaxaca
    0.13
     Medell
    0.13
     Colombia
    0.12
    Claro
    0.12
    Activations Density 0.097%

    No Known Activations