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. 98129
    Prev
    Next
    INDEX
    Explanations

    tpl

    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
     ઉપ
    -0.08
    _TRA
    -0.08
    chini
    -0.08
     ട്ര
    -0.08
    Filt
    -0.08
     ([]
    -0.07
    (Unit
    -0.07
    퓨
    -0.07
     ট্র
    -0.07
    신
    -0.07
    POSITIVE LOGITS
    ib
    0.10
    .SM
    0.09
    awner
    0.08
    lib
    0.08
    öger
    0.08
    ும்ப
    0.08
    aw
    0.08
     ity
    0.08
    artar
    0.08
    ustomed
    0.08
    Activations Density 0.000%

    No Known Activations