© 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. 102269
    Prev
    Next
    INDEX
    Explanations

    decisions

    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
     (+
    -0.08
    ยน
    -0.08
    _original
    -0.08
    1
    -0.08
    -print
    -0.08
    _standard
    -0.08
     currently
    -0.07
    ?family
    -0.07
     №
    -0.07
    #ifdef
    -0.07
    POSITIVE LOGITS
     decisions
    0.17
     keuzes
    0.16
     Entscheidungen
    0.15
     choices
    0.14
     નિર્ણ
    0.14
     décisions
    0.14
     everything
    0.14
     decisiones
    0.14
     ontwerp
    0.13
     Decisions
    0.13
    Activations Density 0.019%

    No Known Activations