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. 112108
    Prev
    Next
    INDEX
    Explanations

    code and programming

    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
     Valentine's
    -0.09
     swing
    -0.09
     turnout
    -0.09
     Valentine
    -0.09
    Swing
    -0.09
     Swing
    -0.08
     Roosevelt
    -0.08
    mittedly
    -0.08
     revolutionary
    -0.08
     papar
    -0.08
    POSITIVE LOGITS
    instantiate
    0.10
    assemble
    0.09
    .optimize
    0.09
    _gpu
    0.08
    .instant
    0.08
     assemble
    0.08
    Tensor
    0.08
    tensor
    0.08
    namespace
    0.08
    Affine
    0.08
    Activations Density 0.002%

    No Known Activations