© 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. 94852
    Prev
    Next
    INDEX
    Explanations

    crop production, climate change

    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
     zool
    -0.09
     reckless
    -0.09
    疯狂
    -0.08
    CES
    -0.08
     patrons
    -0.08
     beve
    -0.08
    Bold
    -0.08
     regained
    -0.08
     proclaimed
    -0.08
     prepar
    -0.08
    POSITIVE LOGITS
     سير
    0.08
    Sequential
    0.08
    אָט
    0.07
    0.07
     Valladolid
    0.07
     Pregnancy
    0.07
     Sequential
    0.07
     Timb
    0.07
     fertility
    0.07
     Evaluation
    0.07
    Activations Density 0.005%
    No Known Activations