© 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. 50319
    Prev
    Next
    INDEX
    Explanations

    S

    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
    232
    -0.07
     directors
    -0.07
     aliquam
    -0.07
    ,b
    -0.07
     arrays
    -0.07
     Bei
    -0.07
     ష
    -0.07
    2
    -0.07
     Eduardo
    -0.07
     isso
    -0.07
    POSITIVE LOGITS
    лава
    0.11
    vät
    0.10
    vět
    0.10
    лаў
    0.10
    лоб
    0.10
    ablja
    0.10
    mě
    0.10
    repen
    0.09
    klif
    0.09
    тарин
    0.09
    Activations Density 0.002%

    No Known Activations