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

    Neuronpedia

    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. 3-RESID-POST-AA
    11. 3050
    Prev
    Next
    INDEX
    Explanations

    blue

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (rest
    -0.08
     philanth
    -0.08
    (Rest
    -0.07
    .Internal
    -0.07
    Parse
    -0.07
    intern
    -0.07
    rf
    -0.07
    IQ
    -0.07
    Rest
    -0.07
     بالأ
    -0.07
    POSITIVE LOGITS
    毛
    0.09
     skies
    0.09
    _spinner
    0.09
    色
    0.09
    /bg
    0.09
    OUT
    0.08
     الوزير
    0.08
     صور
    0.08
     Spinner
    0.08
    mæ
    0.08
    Activations Density 0.003%

    No Known Activations