© 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. 23-RESID-POST-AA
    11. 6190
    Prev
    Next
    INDEX
    Explanations

    team

    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
     radiation
    -0.08
     moll
    -0.07
     चलचित्र
    -0.07
     قبر
    -0.07
     wax
    -0.07
    黄片
    -0.07
     minyak
    -0.07
     pollut
    -0.07
     pagg
    -0.07
     पदार्थ
    -0.07
    POSITIVE LOGITS
     team
    0.67
     Team
    0.64
    Team
    0.64
    (team
    0.63
     टीम
    0.63
    _team
    0.63
     ટીમ
    0.63
     ತಂಡ
    0.61
     팀
    0.60
    team
    0.60
    Activations Density 0.076%

    No Known Activations