© 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. 68087
    Prev
    Next
    INDEX
    Explanations

    his

    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
     bv
    -0.08
     TVs
    -0.08
     cases
    -0.08
    /topics
    -0.07
    /views
    -0.07
    .matmul
    -0.07
    /help
    -0.07
    дв
    -0.07
    муля
    -0.07
     sinking
    -0.07
    POSITIVE LOGITS
     financi
    0.09
     ennem
    0.08
     الإنسان
    0.08
     ism
    0.08
     alian
    0.08
     enem
    0.08
     capita
    0.08
     Verte
    0.08
     الإنسانية
    0.08
     propre
    0.08
    Activations Density 0.001%

    No Known Activations