© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 63742
    Prev
    Next
    INDEX
    Explanations

    server, running, connecting

    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
     оплаты
    -0.08
     Worksheets
    -0.08
     Division
    -0.08
     divisible
    -0.08
     суммы
    -0.08
     фотограф
    -0.08
     округ
    -0.07
     каждого
    -0.07
    (circle
    -0.07
     фотографии
    -0.07
    POSITIVE LOGITS
     hosting
    0.13
    运行
    0.11
     nginx
    0.11
     draaien
    0.11
     hosted
    0.11
     daemon
    0.11
     hosts
    0.10
     Hosting
    0.10
    daemon
    0.10
     laufen
    0.10
    Activations Density 0.037%

    No Known Activations