© 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. 103402
    Prev
    Next
    INDEX
    Explanations

    providing steps/tips/examples

    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
     associated
    -0.12
     or
    -0.10
    Associated
    -0.10
    _that
    -0.10
    或者
    -0.10
    associated
    -0.10
     that
    -0.10
     whereby
    -0.10
     wherein
    -0.10
     representing
    -0.09
    POSITIVE LOGITS
     qty
    0.10
     tz
    0.09
     รีวิว
    0.09
     ျမန္မာ
    0.08
    ၊
    0.08
     ../
    0.08
     రూ
    0.08
    tym
    0.08
     NZ
    0.08
    ทธิ
    0.08
    Activations Density 0.071%

    No Known Activations