© 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. 19-RESID-POST-AA
    11. 102751
    Prev
    Next
    INDEX
    Explanations

    Biological and chemical processes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Disclaimer
    -0.10
     disclaimer
    -0.09
    ございました
    -0.09
     בנושא
    -0.09
     DISCLAIMER
    -0.08
     themed
    -0.08
    Disclaimer
    -0.08
    免责声明
    -0.08
     README
    -0.08
     canned
    -0.08
    POSITIVE LOGITS
     pathways
    0.14
     molecules
    0.12
     processes
    0.12
     организм
    0.12
     процессов
    0.11
     receptors
    0.11
     particles
    0.11
     الجسم
    0.10
     процессы
    0.10
     وبالتالي
    0.10
    Activations Density 0.359%

    No Known Activations