© 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. 102914
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     their
    -0.08
     यी
    -0.08
     Pfizer
    -0.08
     spices
    -0.08
     peux
    -0.08
     المسلمين
    -0.07
    ื
    -0.07
    ↵
    -0.07
     software
    -0.07
     can
    -0.07
    POSITIVE LOGITS
     нескольких
    0.12
     несколько
    0.11
     Several
    0.11
     handful
    0.11
     varios
    0.11
     несколь
    0.11
     várias
    0.10
    Several
    0.10
     бірнеше
    0.10
     někol
    0.10
    Activations Density 0.003%

    No Known Activations