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. 53132
    Prev
    Next
    INDEX
    Explanations

    fails

    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
     pous
    -0.08
     Tiv
    -0.07
     прод
    -0.07
     Bethesda
    -0.07
     kini
    -0.07
     guided
    -0.07
     Cas
    -0.07
     Agro
    -0.07
     Dame
    -0.07
     opus
    -0.07
    POSITIVE LOGITS
     violate
    0.11
    掉
    0.11
     violates
    0.11
    viol
    0.10
    违反
    0.10
     violated
    0.09
     horribly
    0.09
    违规
    0.09
     violating
    0.09
    Incorrect
    0.09
    Activations Density 0.013%

    No Known Activations