Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 98326
    Prev
    Next
    INDEX
    Explanations

    automatic transmissions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gemstone
    -0.09
     gemstones
    -0.09
     décoration
    -0.09
     resized
    -0.09
     Rhin
    -0.08
    gef
    -0.08
     grö
    -0.08
     vezet
    -0.08
     verjaardag
    -0.08
     prowad
    -0.08
    POSITIVE LOGITS
     paddle
    0.09
     continuamente
    0.09
     Tip
    0.09
     자동
    0.09
    자동
    0.09
     otomatis
    0.09
     controlar
    0.09
     automated
    0.08
     automatic
    0.08
     shuttle
    0.08
    Activations Density 0.006%

    No Known Activations