© 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. 19-RESID-POST-AA
    11. 102375
    Prev
    Next
    INDEX
    Explanations

    percentages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     无极
    -0.08
     (...)
    -0.08
    usahaan
    -0.08
     [-
    -0.08
    khiqizo
    -0.08
     (-
    -0.08
     [...]
    -0.08
     outer
    -0.07
    Kõ
    -0.07
     (\
    -0.07
    POSITIVE LOGITS
     liters
    0.13
     percentage
    0.13
    Percentage
    0.13
     শতাংশ
    0.13
     Percentage
    0.13
    percentage
    0.13
     ശതമ
    0.13
     فیصد
    0.12
     ટકા
    0.12
    _percentage
    0.12
    Activations Density 0.042%

    No Known Activations