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. 112148
    Prev
    Next
    INDEX
    Explanations

    proportion

    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
     proteins
    -0.08
     tuples
    -0.08
    .quit
    -0.08
     годов
    -0.08
    .fetch
    -0.07
    ('\
    -0.07
    �
    -0.07
    jies
    -0.07
    ISTS
    -0.07
    觀
    -0.07
    POSITIVE LOGITS
     justified
    0.11
     justification
    0.10
    合理
    0.10
     warranted
    0.10
     ನ್ಯಾಯ
    0.10
     न्याय
    0.09
     Extraordinary
    0.09
     necessity
    0.09
     razo
    0.09
     legitimate
    0.09
    Activations Density 0.019%

    No Known Activations