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. 4
    Prev
    Next
    INDEX
    Explanations

    already

    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
     Republican
    -0.09
     العظيم
    -0.08
     conjunto
    -0.08
     сочет
    -0.08
     resurgence
    -0.08
     Quarterly
    -0.08
     plight
    -0.08
     коэффици
    -0.08
     الجمه
    -0.08
     جودة
    -0.08
    POSITIVE LOGITS
    已经
    0.12
     ఇప్పటికే
    0.11
     progressed
    0.11
     already
    0.11
     已
    0.11
     bereits
    0.11
     commencement
    0.10
    已
    0.10
     hasn't
    0.10
     commenced
    0.10
    Activations Density 0.015%

    No Known Activations