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. 91069
    Prev
    Next
    INDEX
    Explanations

    FROM

    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
    .flush
    -0.08
     extracurricular
    -0.07
    Flush
    -0.07
     الفصل
    -0.07
     collegiate
    -0.07
     college
    -0.07
     Vind
    -0.07
     blooms
    -0.07
     Προ
    -0.07
     ssize
    -0.07
    POSITIVE LOGITS
     좀
    0.09
    _STRING
    0.08
     немного
    0.08
    🏻
    0.08
     결국
    0.07
     पत्रकार
    0.07
     illustrating
    0.07
    orol
    0.07
     Jans
    0.07
     अशी
    0.07
    Activations Density 0.000%

    No Known Activations