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. 43875
    Prev
    Next
    INDEX
    Explanations

    data transformations

    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
     Wire
    -0.08
     Samm
    -0.08
     travers
    -0.08
     wires
    -0.08
     national
    -0.07
     illegally
    -0.07
    .Ass
    -0.07
     overr
    -0.07
     shepherd
    -0.07
     quickly
    -0.07
    POSITIVE LOGITS
     transformations
    0.12
     logarith
    0.11
     ln
    0.11
     transformed
    0.11
    _transform
    0.11
     normalization
    0.11
    Transformation
    0.10
     normalize
    0.10
    Normalize
    0.10
    Transform
    0.10
    Activations Density 0.005%

    No Known Activations