© 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 EvalsExportsinterp-engineNEWAPI 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. 50595
    Prev
    Next
    INDEX
    Explanations

    .k

    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
     chất
    -0.08
     diverso
    -0.08
     כי
    -0.08
     tradicionais
    -0.08
     kah
    -0.07
     फोटो
    -0.07
     PHOTO
    -0.07
     Checks
    -0.07
     pakati
    -0.07
     heraus
    -0.07
    POSITIVE LOGITS
    .a
    0.15
    .ar
    0.09
    -a
    0.09
    ూ
    0.09
    _a
    0.09
    arr
    0.08
     arcs
    0.08
    .up
    0.08
    +a
    0.08
    .addr
    0.08
    Activations Density 0.001%

    No Known Activations