© 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. 3-RESID-POST-AA
    11. 2763
    Prev
    Next
    INDEX
    Explanations

    picture

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Dedicated
    -0.08
     terbaru
    -0.07
     Dedicated
    -0.07
     geldi
    -0.07
    configured
    -0.07
    orlu
    -0.07
    cook
    -0.07
    Vos
    -0.07
     extraordinarily
    -0.07
    azeera
    -0.07
    POSITIVE LOGITS
     endot
    0.10
     scenery
    0.08
     talks
    0.08
     момен
    0.07
     помен
    0.07
     началь
    0.07
     diagrams
    0.07
     quest
    0.07
     patria
    0.07
     suing
    0.07
    Activations Density 0.012%

    No Known Activations