© 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. 29482
    Prev
    Next
    INDEX
    Explanations

    /imagine command

    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
     bookkeeping
    -0.09
    *******************************************************************************↵
    -0.08
     doel
    -0.08
    他的
    -0.08
     analogous
    -0.08
    WOOD
    -0.08
    نن
    -0.08
    န
    -0.08
    ା
    -0.08
    ichí
    -0.08
    POSITIVE LOGITS
     soles
    0.08
     పర
    0.07
    /sec
    0.07
    /gpl
    0.07
     Interactive
    0.07
     Tough
    0.07
     लगा
    0.07
    ?family
    0.07
    /@
    0.07
     నుం�
    0.07
    Activations Density 0.004%

    No Known Activations