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. 43735
    Prev
    Next
    INDEX
    Explanations

    structural supports

    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
    授权
    -0.08
    愛
    -0.08
     sẻ
    -0.08
    RON
    -0.08
    愛い
    -0.08
     bort
    -0.08
     insiders
    -0.07
     tingkat
    -0.07
     contag
    -0.07
     concord
    -0.07
    POSITIVE LOGITS
     taller
    0.10
     thrust
    0.09
     pillars
    0.09
     tower
    0.09
    柱
    0.09
     erected
    0.09
     tallest
    0.09
     towers
    0.09
     topp
    0.08
     tall
    0.08
    Activations Density 0.018%

    No Known Activations