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. 11-RESID-POST-AA
    6. 60784
    Prev
    Next
    INDEX
    Explanations

    y

    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
    .Out
    -0.08
     第一
    -0.08
     extravag
    -0.08
     angekünd
    -0.08
     (>
    -0.07
     exclaimed
    -0.07
    》中
    -0.07
     towering
    -0.07
     Vineyard
    -0.07
    .Groups
    -0.07
    POSITIVE LOGITS
     smaller
    0.11
     comparatively
    0.10
     lesser
    0.10
     humble
    0.10
    াটো
    0.10
     Smaller
    0.09
     мень
    0.09
     humilde
    0.09
     modest
    0.09
     humild
    0.09
    Activations Density 0.212%

    No Known Activations