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. 26838
    Prev
    Next
    INDEX
    Explanations

    determinant calculation

    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
     Locked
    -0.08
    Locked
    -0.08
     fortement
    -0.07
     discovers
    -0.07
    άλι
    -0.07
     Lebensmittel
    -0.07
     jami
    -0.07
     basics
    -0.07
     Jak
    -0.07
    әл
    -0.07
    POSITIVE LOGITS
     irrelevant
    0.09
     mag
    0.08
     hoef
    0.08
     의해
    0.08
     종
    0.08
     hoeven
    0.07
     নগ
    0.07
     prejudice
    0.07
     negligible
    0.07
     yere
    0.07
    Activations Density 0.017%

    No Known Activations