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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 120406
    Prev
    Next
    INDEX
    Explanations

    Mexico

    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
    OSC
    -0.09
     kalau
    -0.08
     agon
    -0.07
     Vag
    -0.07
    惯
    -0.07
    יו
    -0.07
    /right
    -0.07
    će
    -0.07
     Ly
    -0.07
    jego
    -0.07
    POSITIVE LOGITS
     gest
    0.08
     Cartier
    0.08
     mexican
    0.08
     mural
    0.08
     Colombian
    0.07
    icana
    0.07
     pocket
    0.07
     Benito
    0.07
     Mexico
    0.07
     Mexican
    0.07
    Activations Density 0.008%

    No Known Activations