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. 130965
    Prev
    Next
    INDEX
    Explanations

    trade/rights

    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
     Checker
    -0.08
     casc
    -0.08
    Fixture
    -0.08
     checker
    -0.08
    Checker
    -0.08
     découvrir
    -0.07
    onk
    -0.07
    소개
    -0.07
    entra
    -0.07
     structuur
    -0.07
    POSITIVE LOGITS
    权
    0.22
    權
    0.20
     trade
    0.19
     权
    0.18
     Trade
    0.17
    _trade
    0.17
     weighing
    0.17
    trade
    0.17
    Trade
    0.17
     компр
    0.16
    Activations Density 0.039%

    No Known Activations