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. 106312
    Prev
    Next
    INDEX
    Explanations

    Organizational Units (OU)

    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
     Britannica
    -0.08
     update
    -0.07
     asym
    -0.07
    pil
    -0.07
    .on
    -0.07
    在线播放
    -0.07
     bund
    -0.07
     Tensor
    -0.07
    在线观看
    -0.07
    سيل
    -0.07
    POSITIVE LOGITS
     subtree
    0.10
     placements
    0.09
     बच्चों
    0.09
     Children
    0.09
    .Users
    0.09
    Children
    0.09
    .children
    0.09
    Hierarchy
    0.09
     situated
    0.08
     குழந்த
    0.08
    Activations Density 0.003%

    No Known Activations