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. 43884
    Prev
    Next
    INDEX
    Explanations

    work

    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
     mica
    -0.08
     wrongdoing
    -0.07
    moment
    -0.07
     basically
    -0.07
     ruwa
    -0.07
    aq
    -0.07
     acid
    -0.07
    명을
    -0.07
     Fc
    -0.07
     Robbins
    -0.07
    POSITIVE LOGITS
     patch
    0.13
    patch
    0.13
     patches
    0.12
    Patch
    0.11
     Patch
    0.11
     patched
    0.11
    _patch
    0.10
     quilt
    0.10
     Quilt
    0.10
     quilts
    0.10
    Activations Density 0.005%

    No Known Activations