© 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. 47802
    Prev
    Next
    INDEX
    Explanations

    pyramid

    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
     Ghost
    -0.08
     ethic
    -0.08
    SHOT
    -0.08
     lou
    -0.08
     nou
    -0.08
    ナー
    -0.07
    रेल
    -0.07
     예방
    -0.07
     infrastrukt
    -0.07
     industry's
    -0.07
    POSITIVE LOGITS
    yll
    0.08
     accomplished
    0.08
     querying
    0.08
     doub
    0.07
     achieved
    0.07
    睛
    0.07
    uent
    0.07
     centros
    0.07
     выполн
    0.07
    Query
    0.07
    Activations Density 0.001%

    No Known Activations