© 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. 65521
    Prev
    Next
    INDEX
    Explanations

    List items/snippets

    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
     aufgrund
    -0.10
     isl
    -0.09
    由于
    -0.08
     Pong
    -0.08
     XElement
    -0.08
     없어
    -0.08
     Cosm
    -0.08
     vanwege
    -0.08
     имеется
    -0.08
     NOR
    -0.08
    POSITIVE LOGITS
     checklist
    0.11
     Checklist
    0.11
     procrast
    0.10
     disciplined
    0.10
    ✨
    0.09
    技巧
    0.09
    Checklist
    0.09
     proactive
    0.09
     proactively
    0.09
    ✅
    0.09
    Activations Density 0.069%

    No Known Activations