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. 130239
    Prev
    Next
    INDEX
    Explanations

    Academic citations (1900s)

    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
    .Shared
    -0.08
     обол
    -0.08
     Expedia
    -0.08
     maso
    -0.08
     kosher
    -0.07
     ASUS
    -0.07
    Wholesale
    -0.07
    noi
    -0.07
     restriction
    -0.07
     investigation
    -0.07
    POSITIVE LOGITS
     confess
    0.09
     famous
    0.09
    经典
    0.09
     classics
    0.09
     berühm
    0.09
     writings
    0.09
     beroemde
    0.08
     impregn
    0.08
     Werke
    0.08
     iconic
    0.08
    Activations Density 0.011%

    No Known Activations