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. 185
    Prev
    Next
    INDEX
    Explanations

    coloring

    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
     commits
    -0.09
    stackoverflow
    -0.09
    minor
    -0.08
    Quelques
    -0.08
    Minor
    -0.08
    apar
    -0.08
     créd
    -0.08
     Grades
    -0.08
    aten
    -0.08
    usest
    -0.08
    POSITIVE LOGITS
    .reward
    0.08
    探索
    0.08
    体验
    0.07
     reward
    0.07
     colori
    0.07
     swap
    0.07
     Hig
    0.07
    Pane
    0.07
    互动
    0.07
     remin
    0.07
    Activations Density 0.002%

    No Known Activations