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. 111737
    Prev
    Next
    INDEX
    Explanations

    mathematical equations

    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
     margin
    -0.08
     verste
    -0.08
    ിഴ
    -0.08
     whimsical
    -0.08
    347
    -0.08
     handbook
    -0.07
    457
    -0.07
     darbu
    -0.07
    "La
    -0.07
     verhalen
    -0.07
    POSITIVE LOGITS
    -ending
    0.07
    রের
    0.07
     ପ
    0.07
    ୍
    0.07
    anning
    0.07
     props
    0.07
    ::$
    0.07
     күй
    0.07
    ার্স
    0.07
    ြ
    0.07
    Activations Density 0.332%

    No Known Activations