© 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. 11-RESID-POST-AA
    11. 890
    Prev
    Next
    INDEX
    Explanations

    Psychology experiments

    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
     overlay
    -0.08
     fitting
    -0.07
    走
    -0.07
    -be
    -0.07
     spi
    -0.07
     not
    -0.07
     thread
    -0.07
    overlay
    -0.07
    Overlay
    -0.07
    ト
    -0.07
    POSITIVE LOGITS
    sete
    0.09
     zapew
    0.09
    ::{
    0.08
     assurer
    0.08
     NAME
    0.08
    AUTHOR
    0.08
    BUS
    0.08
     Base
    0.08
     prec
    0.08
     creed
    0.08
    Activations Density 0.000%

    No Known Activations