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. 15-RESID-POST-AA
    6. 19117
    Prev
    Next
    INDEX
    Explanations

    Math/geometry

    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
     çeşitli
    -0.08
     predstavlja
    -0.08
     verschiedene
    -0.08
    ונט
    -0.08
    Various
    -0.08
     verschillende
    -0.08
    حيح
    -0.07
    Following
    -0.07
     müxtəlif
    -0.07
     বিভিন্ন
    -0.07
    POSITIVE LOGITS
    一样
    0.12
     alike
    0.09
     LOW
    0.08
     SAME
    0.08
     COLL
    0.08
     ihany
    0.08
    igts
    0.08
    一起
    0.08
    一致
    0.08
     gleicher
    0.08
    Activations Density 0.034%

    No Known Activations