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. 11-RESID-POST-AA
    6. 52957
    Prev
    Next
    INDEX
    Explanations

    file access and manipulation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Colors
    -0.10
    .colors
    -0.09
     trend
    -0.08
     colors
    -0.08
    .icons
    -0.08
    _colors
    -0.08
    colors
    -0.08
     Ер
    -0.08
    Trend
    -0.08
     colorful
    -0.08
    POSITIVE LOGITS
    (offset
    0.13
     offset
    0.11
     offsets
    0.11
    位置
    0.11
     Offset
    0.11
    -offset
    0.11
    (start
    0.11
    .Offset
    0.11
    offset
    0.11
    _offset
    0.10
    Activations Density 0.011%

    No Known Activations