© 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. 63481
    Prev
    Next
    INDEX
    Explanations

    android

    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
     masquer
    -0.07
    (Security
    -0.07
    $form
    -0.07
    േ
    -0.07
    േ�
    -0.07
     amare
    -0.07
     seminars
    -0.07
    ়
    -0.07
     croire
    -0.07
     temps
    -0.07
    POSITIVE LOGITS
    .Basic
    0.09
     fortunately
    0.08
    basic
    0.08
     básica
    0.07
    едения
    0.07
    ед
    0.07
    ascus
    0.07
    of
    0.07
     gick
    0.07
    Basic
    0.07
    Activations Density 0.000%

    No Known Activations