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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 30167
    Prev
    Next
    INDEX
    Explanations

    def

    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
     leit
    -0.09
    yske
    -0.08
     cabel
    -0.08
     tweak
    -0.08
     happ
    -0.08
     Dien
    -0.08
     modificación
    -0.07
     tính
    -0.07
    hout
    -0.07
    슬
    -0.07
    POSITIVE LOGITS
     nestled
    0.09
     वैसे
    0.08
     நேர
    0.08
     irresistible
    0.08
     impuestos
    0.08
    Unified
    0.08
     ecological
    0.07
     काळ
    0.07
    .bs
    0.07
    वे
    0.07
    Activations Density 0.001%

    No Known Activations