© 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. 23-RESID-POST-AA
    11. 49463
    Prev
    Next
    INDEX
    Explanations

    enzymes and transferases

    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
     Washing
    -0.09
    Twenty
    -0.08
     шест
    -0.08
     washing
    -0.08
     gp
    -0.08
     يول
    -0.08
     Six
    -0.08
     цикл
    -0.08
     Thirty
    -0.08
     twelve
    -0.08
    POSITIVE LOGITS
    Query
    0.08
    fer
    0.08
    nst
    0.08
     உயிர
    0.08
    Fer
    0.08
    Crud
    0.08
    oyinka
    0.07
    amin
    0.07
    ium
    0.07
    Ń
    0.07
    Activations Density 0.000%

    No Known Activations