© 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. 23-RESID-POST-AA
    11. 47856
    Prev
    Next
    INDEX
    Explanations

    Made

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _stop
    -0.09
     stop
    -0.08
     stops
    -0.08
    -ended
    -0.08
    STOP
    -0.08
    ائص
    -0.08
    _STOP
    -0.08
    -stop
    -0.08
     três
    -0.08
     dada
    -0.07
    POSITIVE LOGITS
    innut
    0.11
    cass
    0.09
    Believe
    0.09
    Simple
    0.08
     nchini
    0.08
    manageable
    0.08
     Specifically
    0.08
    leine
    0.08
     ભારતમાં
    0.08
     Their
    0.08
    Activations Density 0.010%

    No Known Activations