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. 43402
    Prev
    Next
    INDEX
    Explanations

    import

    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
    /example
    -0.08
     drawbacks
    -0.08
    `()
    -0.08
     pictured
    -0.07
     عقل
    -0.07
     നോ
    -0.07
    ാധ്യമ
    -0.07
    vär
    -0.07
     Trip
    -0.07
     의해
    -0.07
    POSITIVE LOGITS
     =============================================================================
    0.08
     tqdm
    0.08
    Clamp
    0.08
    RAF
    0.07
    opup
    0.07
     herein
    0.07
     ausschließlich
    0.07
     führte
    0.07
     тен
    0.07
     concurrency
    0.07
    Activations Density 0.011%

    No Known Activations