© 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. 19-RESID-POST-AA
    11. 102685
    Prev
    Next
    INDEX
    Explanations

    human

    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
     experto
    -0.07
    タグ
    -0.07
    مخت
    -0.07
    node
    -0.07
    יסה
    -0.07
     Hoje
    -0.07
     Mercado
    -0.07
    바사
    -0.07
     Украине
    -0.07
     hires
    -0.07
    POSITIVE LOGITS
    ewise
    0.11
    -an
    0.11
    'an
    0.10
    ’an
    0.10
    ely
    0.10
     μεγαλ
    0.09
    anasia
    0.09
    -An
    0.09
     також
    0.09
    ане
    0.09
    Activations Density 0.003%

    No Known Activations