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. 60581
    Prev
    Next
    INDEX
    Explanations

    header

    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
     crude
    -0.08
    qi
    -0.08
     lumin
    -0.08
     incubation
    -0.08
    Synchronization
    -0.07
     avi
    -0.07
     represented
    -0.07
    loj
    -0.07
     তর
    -0.07
    represented
    -0.07
    POSITIVE LOGITS
     sections
    0.09
     내부
    0.08
    녕하세요
    0.07
    挺
    0.07
    Content
    0.07
    .sections
    0.07
    .Xml
    0.07
     mistakes
    0.07
    pizza
    0.07
    .tv
    0.07
    Activations Density 0.005%

    No Known Activations