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. 41953
    Prev
    Next
    INDEX
    Explanations

    def

    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
     sek
    -0.08
    惜
    -0.07
     واله
    -0.07
    悠
    -0.07
    quently
    -0.07
    sects
    -0.07
    森
    -0.07
    Sparse
    -0.07
     memoir
    -0.07
    ування
    -0.07
    POSITIVE LOGITS
     స్పంద
    0.08
    (response
    0.08
     Louise
    0.08
     response
    0.08
     IB
    0.08
    _response
    0.08
     प्रतिक्रिया
    0.08
     departing
    0.08
    .dep
    0.07
    _handler
    0.07
    Activations Density 0.002%

    No Known Activations