© 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. 54785
    Prev
    Next
    INDEX
    Explanations

    History of energy

    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
     પહેલા
    -0.08
     ઉપરાંત
    -0.08
     તમારા
    -0.08
     برند
    -0.08
    いう
    -0.08
     પૂર્વ
    -0.08
     així
    -0.08
     વડ
    -0.08
     استان
    -0.08
     nochmal
    -0.08
    POSITIVE LOGITS
    atio
    0.08
     emerged
    0.08
    ε
    0.08
     ε
    0.08
    vare
    0.07
    dialog
    0.07
     sailors
    0.07
     ди
    0.07
    ster
    0.07
    λ
    0.07
    Activations Density 0.248%

    No Known Activations