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. 44087
    Prev
    Next
    INDEX
    Explanations

    cells

    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
     repos
    -0.08
     вещи
    -0.08
    作品
    -0.08
     exped
    -0.08
     verdad
    -0.08
     stash
    -0.08
     عنوان
    -0.07
     unpopular
    -0.07
     quot
    -0.07
    ყ
    -0.07
    POSITIVE LOGITS
    ocytes
    0.14
     cells
    0.13
     neurons
    0.11
     endothelial
    0.11
     lining
    0.11
     Cells
    0.10
    cells
    0.10
    _cells
    0.10
    .cells
    0.10
     cellules
    0.10
    Activations Density 0.011%

    No Known Activations