© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 8026
    Prev
    Next
    INDEX
    Explanations

    leader

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     گذ
    -0.08
    ễ
    -0.08
     recharge
    -0.08
     intégr
    -0.07
     slab
    -0.07
     milj
    -0.07
     πρά
    -0.07
     indulg
    -0.07
     slurry
    -0.07
     laundry
    -0.07
    POSITIVE LOGITS
     liderança
    0.12
    领导
    0.11
     coordinating
    0.11
     liderazgo
    0.11
     líder
    0.11
     नेतृत्व
    0.11
     నాయక
    0.11
     നേതൃത്വം
    0.10
     Among
    0.10
     overseeing
    0.10
    Activations Density 0.085%

    No Known Activations