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. 52664
    Prev
    Next
    INDEX
    Explanations

    Extracts quotes and reasoning

    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
    ージ
    -0.08
    ipsoid
    -0.08
    -0.08
     jednom
    -0.07
     primitives
    -0.07
    жел
    -0.07
     gerçek
    -0.07
    骨
    -0.07
    日日
    -0.07
    [min
    -0.07
    POSITIVE LOGITS
     inferred
    0.10
     त्यांनी
    0.08
     been
    0.08
     alleged
    0.07
     أحدث
    0.07
    Beat
    0.07
    Award
    0.07
     allegations
    0.07
    ов
    0.07
    ség
    0.07
    Activations Density 0.086%

    No Known Activations