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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 59387
    Prev
    Next
    INDEX
    Explanations

    Arc de Triomphe

    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
     hovering
    -0.08
    .bucket
    -0.08
     bont
    -0.08
     roster
    -0.08
     qb
    -0.08
     però
    -0.07
     quota
    -0.07
    239
    -0.07
     slot
    -0.07
    .Pod
    -0.07
    POSITIVE LOGITS
     kaldır
    0.08
     ರಾಜ
    0.08
    (Adapter
    0.08
     rallies
    0.07
    しょう
    0.07
    asters
    0.07
    广告
    0.07
     русского
    0.07
    広告
    0.07
     Malaysian
    0.07
    Activations Density 0.002%

    No Known Activations