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. 98078
    Prev
    Next
    INDEX
    Explanations

    Calculations and numbers

    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
    _renderer
    -0.09
     osm
    -0.08
    inch
    -0.08
    уст
    -0.08
    _sampler
    -0.08
    awu
    -0.08
     Gen
    -0.08
     crab
    -0.07
    jn
    -0.07
    ит
    -0.07
    POSITIVE LOGITS
    204
    0.19
    404
    0.16
    Queue
    0.16
     Council
    0.16
     Queue
    0.16
     Park
    0.15
     Cart
    0.15
    Cart
    0.15
    Council
    0.14
    (Menu
    0.14
    Activations Density 0.038%

    No Known Activations