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. 30037
    Prev
    Next
    INDEX
    Explanations

    Wormholes and exotic matter

    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
     cereal
    -0.08
     serializer
    -0.08
     påver
    -0.08
     blir
    -0.08
     bild
    -0.08
     kanal
    -0.08
     waved
    -0.08
     Db
    -0.08
    大家
    -0.08
    影
    -0.08
    POSITIVE LOGITS
     exotic
    0.09
     Exotic
    0.08
    Ó
    0.08
    Negative
    0.08
    Fraction
    0.08
    _Remove
    0.08
    Preço
    0.08
    cred
    0.08
    (AL
    0.08
     borrowed
    0.08
    Activations Density 0.001%

    No Known Activations