© 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. 68972
    Prev
    Next
    INDEX
    Explanations

    only

    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
    .mix
    -0.07
     electroph
    -0.07
     جه
    -0.07
    וז
    -0.07
    _Handler
    -0.07
    aline
    -0.07
    ساهم
    -0.07
    .enqueue
    -0.07
    ಳೆ
    -0.07
    نز
    -0.07
    POSITIVE LOGITS
     (...
    0.08
     obligatorio
    0.08
     bedoeld
    0.08
    用途
    0.08
     strictly
    0.08
     Trainings
    0.07
    centes
    0.07
    Issued
    0.07
     الاستخدام
    0.07
    ried
    0.07
    Activations Density 0.029%

    No Known Activations