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. 23-RESID-POST-AA
    6. 130947
    Prev
    Next
    INDEX
    Explanations

    0

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Jagu
    -0.08
     Mardi
    -0.08
     уру
    -0.08
    จำวันที่
    -0.07
    იას
    -0.07
    .live
    -0.07
     الني
    -0.07
     ნაც
    -0.07
     Cus
    -0.07
     fiestas
    -0.07
    POSITIVE LOGITS
     h
    0.25
     height
    0.25
    height
    0.24
    Height
    0.23
    _height
    0.23
     Height
    0.23
    h
    0.22
    .height
    0.22
     altura
    0.22
     heights
    0.21
    Activations Density 0.056%

    No Known Activations