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. 60991
    Prev
    Next
    INDEX
    Explanations

    Anime/Manga

    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
     Outlet
    -0.09
     Grö
    -0.09
     Tripadvisor
    -0.08
     फेसबुक
    -0.08
    .booking
    -0.08
     ప్రేక్షక
    -0.08
     POST
    -0.08
     Fixture
    -0.08
     MSNBC
    -0.08
    gettext
    -0.08
    POSITIVE LOGITS
     glands
    0.09
     Sakura
    0.08
    Ⅰ
    0.08
    武
    0.08
    Force
    0.08
    悟
    0.08
     chakra
    0.08
    Hide
    0.08
     terror
    0.07
    〇
    0.07
    Activations Density 0.013%

    No Known Activations