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. 42282
    Prev
    Next
    INDEX
    Explanations

    more

    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
     وبالتالي
    -0.08
    rump
    -0.08
     pursuits
    -0.08
    ивание
    -0.07
    undy
    -0.07
     대상으로
    -0.07
    #endif
    -0.07
    ющихся
    -0.07
    917
    -0.07
    Och
    -0.07
    POSITIVE LOGITS
     guidance
    0.10
     FAQ
    0.10
     FAQs
    0.09
     Guidance
    0.09
     faq
    0.09
     Anleitung
    0.09
     juridische
    0.09
    FAQ
    0.09
     erläut
    0.09
     правила
    0.08
    Activations Density 0.064%

    No Known Activations