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. 76265
    Prev
    Next
    INDEX
    Explanations

    be

    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
    quelas
    -0.09
     emergence
    -0.08
    (factory
    -0.08
     mob
    -0.07
    peas
    -0.07
    pey
    -0.07
    /docs
    -0.07
     pax
    -0.07
    PIO
    -0.07
    fifo
    -0.07
    POSITIVE LOGITS
     thorough
    0.09
     под
    0.09
     doctoral
    0.09
     clarity
    0.08
     formal
    0.08
     Bayesian
    0.08
     Lui
    0.08
     systematic
    0.08
     Kapoor
    0.08
     prudent
    0.08
    Activations Density 0.010%

    No Known Activations