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. 44114
    Prev
    Next
    INDEX
    Explanations

    vegetarian

    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
     Auditorium
    -0.08
    iffel
    -0.08
    vil
    -0.08
    -lhes
    -0.08
     개최
    -0.08
    August
    -0.08
     이야기
    -0.08
     troupe
    -0.08
     존재
    -0.08
     matchmaking
    -0.07
    POSITIVE LOGITS
     vegan
    0.10
     keto
    0.10
     avoids
    0.10
     vegetarian
    0.10
     vegetar
    0.09
     evitando
    0.08
     intact
    0.08
     evitar
    0.08
     نبات
    0.08
     ketogenic
    0.08
    Activations Density 0.012%

    No Known Activations