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. 58519
    Prev
    Next
    INDEX
    Explanations

    actor-network theory

    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
     الشعر
    -0.09
     insult
    -0.08
     abdominal
    -0.08
     melanch
    -0.08
     Körpers
    -0.08
    Seeder
    -0.08
     회원
    -0.08
     피부
    -0.08
     gift
    -0.08
     insulting
    -0.07
    POSITIVE LOGITS
     disparition
    0.09
     silo
    0.08
     réseau
    0.08
     regels
    0.07
    bureau
    0.07
    もちろん
    0.07
     монта
    0.07
    -tabs
    0.07
    ిణ
    0.07
    /network
    0.07
    Activations Density 0.015%

    No Known Activations