© 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. 49318
    Prev
    Next
    INDEX
    Explanations

    say "без" words

    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
     outright
    -0.11
     оказалось
    -0.08
    ouncing
    -0.08
    uwen
    -0.08
    억
    -0.08
     outward
    -0.08
     sufficiently
    -0.08
    ufficient
    -0.07
    aying
    -0.07
    nington
    -0.07
    POSITIVE LOGITS
     преж
    0.09
     válto
    0.09
     нет
    0.09
     nguyên
    0.09
     जस
    0.08
     tal
    0.08
     onver
    0.08
     invari
    0.08
     unver
    0.08
     Lista
    0.08
    Activations Density 0.003%

    No Known Activations