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. 15-RESID-POST-AA
    6. 19202
    Prev
    Next
    INDEX
    Explanations

    code, programming

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     julka
    -0.09
     ejecut
    -0.09
    publ
    -0.09
     anunci
    -0.08
    printing
    -0.08
    publish
    -0.08
     spus
    -0.08
     announced
    -0.08
     puesta
    -0.08
     estoy
    -0.08
    POSITIVE LOGITS
     Aussagen
    0.08
    (Movie
    0.08
    (sprite
    0.08
    (color
    0.08
    (routes
    0.07
    (simple
    0.07
    (Simple
    0.07
    (colors
    0.07
     Gardner
    0.07
     цвета
    0.07
    Activations Density 0.001%

    No Known Activations