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

    Neuronpedia

    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. 99493
    Prev
    Next
    INDEX
    Explanations

    .

    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
    -साथ
    -0.08
     टिक
    -0.08
     endure
    -0.07
    _Request
    -0.07
     গুরুত্ব
    -0.07
    _Tag
    -0.07
     abre
    -0.07
    ///<
    -0.07
     endurance
    -0.07
     учиты
    -0.07
    POSITIVE LOGITS
     ultr
    0.07
     Ministry
    0.07
     ICS
    0.07
     Anadolu
    0.07
    онч
    0.07
     chamber
    0.07
    iate
    0.07
     rho
    0.07
     cavity
    0.07
     LAB
    0.07
    Activations Density 0.003%

    No Known Activations