Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 18860
    Prev
    Next
    INDEX
    Explanations

    Parentheses

    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
    江
    -0.09
    人民日报
    -0.09
     江
    -0.09
    杭州
    -0.09
    中华
    -0.09
    693
    -0.08
    广州
    -0.08
    我国
    -0.08
    云南
    -0.08
    江西
    -0.08
    POSITIVE LOGITS
     (`
    0.23
     ("
    0.21
     (
    0.18
     ('
    0.18
     (_
    0.17
     (\
    0.17
     («
    0.16
     (*
    0.16
    (
    0.16
     ($
    0.16
    Activations Density 0.245%

    No Known Activations