© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 49263
    Prev
    Next
    INDEX
    Explanations

    Leadership

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     medically
    -0.09
     medizin
    -0.09
     exemptions
    -0.09
     seizures
    -0.08
     flagged
    -0.08
     wagers
    -0.07
     vigil
    -0.07
    ambula
    -0.07
     bail
    -0.07
    elaide
    -0.07
    POSITIVE LOGITS
     managerial
    0.16
     Organizational
    0.16
     Druck
    0.14
     organizational
    0.14
     Leadership
    0.13
     నాయక
    0.13
     नेतृत्व
    0.13
     Gestão
    0.13
     Führung
    0.13
     الإدارة
    0.13
    Activations Density 0.050%

    No Known Activations