© 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. 102303
    Prev
    Next
    INDEX
    Explanations

    say watch

    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
     avoiding
    -0.09
     ocas
    -0.09
     somewhat
    -0.09
     يمكنك
    -0.09
    避免
    -0.09
    因为
    -0.09
     avoids
    -0.09
     如果
    -0.09
     Because
    -0.09
    如果
    -0.08
    POSITIVE LOGITS
    Definitely
    0.09
     tentu
    0.09
    becca
    0.09
    abulous
    0.09
     Definitely
    0.09
    (be
    0.09
     sure
    0.09
     অবশ্য
    0.08
     sûrement
    0.08
    (Be
    0.08
    Activations Density 0.021%

    No Known Activations