© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 7787
    Prev
    Next
    INDEX
    Explanations

    EU policy and law

    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
     baseball
    -0.11
    .firebase
    -0.09
     Hawaiian
    -0.09
    .firebaseio
    -0.09
     Baylor
    -0.09
     NSObject
    -0.09
     cuz
    -0.09
     awhile
    -0.09
     Sabbath
    -0.09
     Dynasty
    -0.09
    POSITIVE LOGITS
    欧洲
    0.15
     यूर
    0.15
     European
    0.15
    European
    0.14
     européenne
    0.14
     euros
    0.14
     Europe
    0.14
     euro
    0.14
     européens
    0.14
     européen
    0.14
    Activations Density 0.147%

    No Known Activations