© 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. 19-RESID-POST-AA
    11. 19024
    Prev
    Next
    INDEX
    Explanations

    commas and and

    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
    's
    -0.13
    의
    -0.09
    —
    -0.09
    (always
    -0.09
     (
    -0.09
    >
    -0.09
    꺼
    -0.09
     –
    -0.09
     →
    -0.08
    _(
    -0.08
    POSITIVE LOGITS
     informative
    0.15
     insightful
    0.14
     detailed
    0.13
     concise
    0.13
     accurate
    0.13
    詳細
    0.12
     detaill
    0.12
     thoughtful
    0.12
    详细
    0.12
     succinct
    0.12
    Activations Density 0.025%

    No Known Activations