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. 19108
    Prev
    Next
    INDEX
    Explanations

    of

    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
     Google
    -0.08
     allerlei
    -0.08
    format
    -0.07
     information
    -0.07
    .Google
    -0.07
     format
    -0.07
    Google
    -0.07
     has
    -0.07
    Exp
    -0.06
     GMT
    -0.06
    POSITIVE LOGITS
     полов
    0.12
     mitad
    0.12
     moitié
    0.12
     Hälfte
    0.12
     helft
    0.11
    -half
    0.10
     الأحيان
    0.10
    分彩
    0.10
     metà
    0.10
    هر
    0.10
    Activations Density 0.018%

    No Known Activations