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. 30638
    Prev
    Next
    INDEX
    Explanations

    Surface tension

    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
     bone
    -0.10
     bones
    -0.09
     иш
    -0.09
     rõ
    -0.08
     ডিজ
    -0.08
     Bone
    -0.08
     sins
    -0.08
     deeply
    -0.08
     fossils
    -0.08
     Seymour
    -0.08
    POSITIVE LOGITS
     pudd
    0.13
     droplets
    0.12
    Fluid
    0.11
     fluid
    0.10
     दूध
    0.10
     liquid
    0.10
     Fluid
    0.10
    液
    0.10
     Liquid
    0.09
     bubble
    0.09
    Activations Density 0.019%

    No Known Activations