© 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. 44778
    Prev
    Next
    INDEX
    Explanations

    clauses and grammar

    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
     partying
    -0.07
     države
    -0.07
     posting
    -0.07
     durumda
    -0.07
     posture
    -0.07
     Transactions
    -0.07
     Tick
    -0.07
     Tray
    -0.07
     Posts
    -0.07
     Transaction
    -0.07
    POSITIVE LOGITS
     уточ
    0.08
    Helpful
    0.08
    ിസ്റ്റ
    0.08
     narrowing
    0.08
     explanatory
    0.08
     aclar
    0.08
    Content
    0.08
    Illustr
    0.08
     പി
    0.08
    maß
    0.08
    Activations Density 0.006%

    No Known Activations