Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 106266
    Prev
    Next
    INDEX
    Explanations

    coding, servers, development

    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
     соверш
    -0.08
     modeled
    -0.08
    urpose
    -0.08
     Rain
    -0.08
    ologies
    -0.08
    ench
    -0.08
    enching
    -0.08
    elem
    -0.07
     ______
    -0.07
     suffer
    -0.07
    POSITIVE LOGITS
     crawling
    0.09
     canlı
    0.09
    Live
    0.09
     cucumber
    0.08
     presses
    0.08
    .Live
    0.08
    Preview
    0.08
     Live
    0.08
     previews
    0.08
    .preview
    0.08
    Activations Density 0.007%

    No Known Activations