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. 112023
    Prev
    Next
    INDEX
    Explanations

    web development debugging

    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
     BIT
    -0.08
     huts
    -0.08
    _bitmap
    -0.07
     inflatable
    -0.07
     prescribed
    -0.07
    prefix
    -0.07
     tão
    -0.07
    Plate
    -0.07
     संभव
    -0.07
    .prefix
    -0.07
    POSITIVE LOGITS
    Inspect
    0.12
     Inspect
    0.12
     инсп
    0.11
    Inspector
    0.11
     inspect
    0.11
     Firefox
    0.10
     inspecting
    0.10
     брауз
    0.10
     inspector
    0.10
    inspect
    0.10
    Activations Density 0.007%

    No Known Activations