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. 48936
    Prev
    Next
    INDEX
    Explanations

    rebuild

    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
    印
    -0.08
    MEA
    -0.08
    Qg
    -0.08
     Kand
    -0.07
     ADV
    -0.07
    cé
    -0.07
    назнач
    -0.07
    pik
    -0.07
    há
    -0.07
     penny
    -0.07
    POSITIVE LOGITS
     Chron
    0.08
     phases
    0.08
     коррект
    0.08
     trying
    0.07
     subtract
    0.07
     neces
    0.07
    <string
    0.07
     satis
    0.07
     plaas
    0.07
     berücksicht
    0.07
    Activations Density 0.001%

    No Known Activations