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

    Neuronpedia

    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. 19-RESID-POST-AA
    11. 103332
    Prev
    Next
    INDEX
    Explanations

    comma

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     широко
    -0.09
    UTC
    -0.08
     still
    -0.08
    indsight
    -0.08
    ugg
    -0.07
    ugl
    -0.07
     більш
    -0.07
     ample
    -0.07
     fleste
    -0.07
     pièce
    -0.07
    POSITIVE LOGITS
     like
    0.10
     contrairement
    0.10
    _middle
    0.09
     unlike
    0.09
    .middle
    0.09
     מיוח
    0.08
    Middle
    0.08
     ");
    0.08
     जैसे
    0.08
     tulad
    0.08
    Activations Density 0.001%

    No Known Activations