© 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. 8174
    Prev
    Next
    INDEX
    Explanations

    10

    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
     injuries
    -0.07
    .Per
    -0.07
    アクセ
    -0.07
     incidence
    -0.07
     Britain
    -0.07
    (num
    -0.07
     inzicht
    -0.07
    man's
    -0.07
    distance
    -0.07
     conquista
    -0.07
    POSITIVE LOGITS
     aanbevolen
    0.09
     recommandé
    0.09
     recommended
    0.09
     Mindest
    0.09
     đảm
    0.09
    zah
    0.08
     غوره
    0.08
     жақсы
    0.08
     preferably
    0.08
     anbef
    0.08
    Activations Density 0.006%

    No Known Activations