© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 63983
    Prev
    Next
    INDEX
    Explanations

    inner

    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
     같이
    -0.08
    이트
    -0.08
    ді
    -0.08
    (reinterpret
    -0.08
     동시에
    -0.08
    iði
    -0.07
     simultaneously
    -0.07
     যাচ্ছে
    -0.07
    jaw
    -0.07
    ibbean
    -0.07
    POSITIVE LOGITS
     clinicians
    0.08
    θο
    0.08
     Echo
    0.08
     opus
    0.08
    Echo
    0.07
     Clin
    0.07
     bartender
    0.07
     empowerment
    0.07
     campeão
    0.07
     prophets
    0.07
    Activations Density 0.005%

    No Known Activations