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. 76316
    Prev
    Next
    INDEX
    Explanations

    family

    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
     abilities
    -0.09
     kemampuan
    -0.07
     Review
    -0.07
    -runtime
    -0.07
    ooker
    -0.07
     /\
    -0.07
    Ps
    -0.07
    anzi
    -0.07
    _resume
    -0.07
    Review
    -0.07
    POSITIVE LOGITS
     tirsan
    0.09
     פארשט
    0.09
     voire
    0.09
    似
    0.09
    ുഞ്ഞ
    0.08
     შეტ
    0.08
     ഭാഗമായി
    0.08
     ಮೃತಪಟ್ಟ
    0.08
     تړ
    0.08
    اقت
    0.08
    Activations Density 0.019%

    No Known Activations