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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 49198
    Prev
    Next
    INDEX
    Explanations

    Disallowed content requests

    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
     गुण
    -0.09
     BUS
    -0.09
     वास्त
    -0.09
     curator
    -0.08
     réserver
    -0.08
     BAND
    -0.08
     stringify
    -0.08
     yam
    -0.08
     बिज
    -0.08
     wind
    -0.07
    POSITIVE LOGITS
     unethical
    0.17
     illicit
    0.15
     ethically
    0.15
     незакон
    0.14
     ilegal
    0.14
     controversial
    0.13
    非法
    0.13
    倫理
    0.13
     illegal
    0.13
     responsibly
    0.13
    Activations Density 0.473%

    No Known Activations