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. 98116
    Prev
    Next
    INDEX
    Explanations

    math calculations

    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
     سخ
    -0.08
     Correspond
    -0.08
     Or
    -0.07
     Kernel
    -0.07
    ικά
    -0.07
     Enterprise
    -0.07
    ieuze
    -0.07
    iece
    -0.07
    ाव
    -0.07
    ما
    -0.07
    POSITIVE LOGITS
    ŋ
    0.08
    /path
    0.07
    anach
    0.07
    め
    0.07
     FIRST
    0.07
    (vars
    0.07
    MD
    0.07
    パ
    0.07
    Beh
    0.07
     teş
    0.07
    Activations Density 0.002%

    No Known Activations