© 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. 18803
    Prev
    Next
    INDEX
    Explanations

    Agreement scales

    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
     unfavorable
    -0.14
     negative
    -0.13
     negatives
    -0.13
    Negative
    -0.13
    bad
    -0.13
     adverse
    -0.13
     bad
    -0.12
    -negative
    -0.12
    _negative
    -0.12
     негатив
    -0.12
    POSITIVE LOGITS
     必胜
    0.10
     Yes
    0.10
     یق
    0.09
     yes
    0.08
    必赢
    0.08
    Yes
    0.08
     ياد
    0.08
     kusema
    0.08
    usionsoft
    0.08
     oui
    0.08
    Activations Density 0.011%

    No Known Activations