Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 117698
    Prev
    Next
    INDEX
    Explanations

    SSH configuration

    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
    undi
    -0.08
     mase
    -0.08
     lampe
    -0.08
     selfies
    -0.08
     Filing
    -0.07
     seri
    -0.07
     meh
    -0.07
     effettu
    -0.07
     dobl
    -0.07
     heroes
    -0.07
    POSITIVE LOGITS
     Winchester
    0.09
     Savannah
    0.08
    erderij
    0.08
    deny
    0.08
    _linux
    0.07
     रक्षा
    0.07
     protéger
    0.07
    _gate
    0.07
    हा
    0.07
    Linux
    0.07
    Activations Density 0.003%

    No Known Activations