© 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. 63918
    Prev
    Next
    INDEX
    Explanations

    function

    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
    _tail
    -0.08
    浪
    -0.08
     crimen
    -0.08
     armado
    -0.08
    .extend
    -0.07
     रु
    -0.07
    .after
    -0.07
     ಠ
    -0.07
     Monopoly
    -0.07
    _make
    -0.07
    POSITIVE LOGITS
     dysfunction
    0.12
     impairment
    0.12
    正常
    0.11
     impaired
    0.11
     Dysfunction
    0.11
     impair
    0.10
     faol
    0.09
     abilities
    0.08
    оспособ
    0.08
     intact
    0.08
    Activations Density 0.015%

    No Known Activations