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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 1522
    Prev
    Next
    INDEX
    Explanations

    ation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     piel
    -0.09
     Bowling
    -0.07
    גיש
    -0.07
     ர
    -0.07
    نية
    -0.07
    axis
    -0.07
     connaiss
    -0.07
    ел
    -0.07
     Ezek
    -0.07
     Md
    -0.07
    POSITIVE LOGITS
    dessen
    0.08
     serem
    0.08
    써
    0.08
    Purpose
    0.08
     onu
    0.08
    -/
    0.07
     palace
    0.07
     bahan
    0.07
    úa
    0.07
    બા
    0.07
    Activations Density 0.061%

    No Known Activations