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. 11773
    Prev
    Next
    INDEX
    Explanations

    sushi

    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
    (font
    -0.08
    ியல்
    -0.08
    language
    -0.08
     stad
    -0.08
     language
    -0.08
    ormap
    -0.07
     Repub
    -0.07
     lze
    -0.07
     inquire
    -0.07
     katal
    -0.07
    POSITIVE LOGITS
     sushi
    0.10
     burger
    0.09
     Sushi
    0.09
     sandwich
    0.09
    Sticky
    0.09
     burgers
    0.09
     cucumber
    0.09
     świe
    0.08
    Wrapping
    0.08
    糖
    0.08
    Activations Density 0.002%

    No Known Activations