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. 15-RESID-POST-AA
    6. 19241
    Prev
    Next
    INDEX
    Explanations

    in

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ulloq
    -0.12
     ʻaʻole
    -0.11
    ებებს
    -0.11
     ۽
    -0.11
     outright
    -0.11
     aaqq
    -0.11
     kisianni
    -0.11
     ʻoe
    -0.10
     მეტი
    -0.10
     ազատ
    -0.10
    POSITIVE LOGITS
    某
    0.10
     certain
    0.09
    **
    0.09
    2
    0.09
    3
    0.09
     **
    0.09
     "
    0.08
     is
    0.08
    1
    0.08
     K
    0.08
    Activations Density 0.036%

    No Known Activations