© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 113276
    Prev
    Next
    INDEX
    Explanations

    but

    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
    gram
    -0.08
    grams
    -0.08
    Diagram
    -0.07
    _station
    -0.07
    ‍ഷം
    -0.07
    iy
    -0.07
    ٥
    -0.07
    文
    -0.07
    ima
    -0.07
    :f
    -0.07
    POSITIVE LOGITS
     supplemented
    0.09
     disguised
    0.09
     pony
    0.08
     accompanied
    0.08
     disguise
    0.08
     kemudian
    0.08
     RB
    0.08
     той
    0.08
     disguis
    0.08
     reloc
    0.08
    Activations Density 0.054%

    No Known Activations