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. 76050
    Prev
    Next
    INDEX
    Explanations

    math symbols

    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
     warming
    -0.08
     warms
    -0.08
     endothelial
    -0.08
    Fol
    -0.08
     triturador
    -0.08
     forslag
    -0.08
     kulit
    -0.08
    Landing
    -0.07
     udvalg
    -0.07
    decltype
    -0.07
    POSITIVE LOGITS
    124
    0.11
    ٥
    0.10
    5
    0.09
    45
    0.09
    ৫
    0.09
    15
    0.09
    404
    0.09
    105
    0.08
    65
    0.08
    ٧
    0.08
    Activations Density 0.066%

    No Known Activations