© 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. 13177
    Prev
    Next
    INDEX
    Explanations

    time and measurement

    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
     средств
    -0.08
    员
    -0.08
    ங்களுக்கு
    -0.08
    ेत्र
    -0.08
     prevailing
    -0.07
    ​យ
    -0.07
    ಗಳಿಂದ
    -0.07
    oneg
    -0.07
    édération
    -0.07
    ದ್ದು
    -0.07
    POSITIVE LOGITS
    jes
    0.08
     pien
    0.08
     Vineyard
    0.08
     pertin
    0.07
     tangled
    0.07
     ect
    0.07
    .hours
    0.07
     Hank
    0.07
     Diagnostics
    0.07
    jana
    0.07
    Activations Density 0.000%

    No Known Activations