© 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. 30934
    Prev
    Next
    INDEX
    Explanations

    described

    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
    odge
    -0.07
     �
    -0.07
    pell
    -0.07
     وهو
    -0.07
     ללמוד
    -0.07
    学
    -0.07
     Discover
    -0.07
     향
    -0.07
     Frei
    -0.07
     limestone
    -0.07
    POSITIVE LOGITS
    subplot
    0.10
     synopsis
    0.09
     subplot
    0.08
    comments
    0.08
    Synopsis
    0.08
     Brief
    0.08
    ინ
    0.08
     حدوث
    0.08
    iav
    0.08
    Brief
    0.08
    Activations Density 0.001%

    No Known Activations