© 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. 3-RESID-POST-AA
    11. 13120
    Prev
    Next
    INDEX
    Explanations

    ource

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     facilidade
    -0.08
     diện
    -0.08
    عامل
    -0.08
     Zucker
    -0.07
    طان
    -0.07
     Epidemi
    -0.07
    амп
    -0.07
     giao
    -0.07
     instancia
    -0.07
    ตร
    -0.07
    POSITIVE LOGITS
     kuni
    0.08
    ುತ್ತಿದ್ದ
    0.08
    ುತ್ತಿರುವ
    0.08
    董
    0.08
     oils
    0.07
    materials
    0.07
    icamente
    0.07
    Sto
    0.07
    一句
    0.07
    我是
    0.07
    Activations Density 0.000%

    No Known Activations