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. 29986
    Prev
    Next
    INDEX
    Explanations

    Random assortment of text

    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
     Pek
    -0.08
     virkelig
    -0.08
    烟
    -0.07
     થ
    -0.07
     gummy
    -0.07
     softball
    -0.07
    พิ
    -0.07
     thermostat
    -0.07
    ournal
    -0.07
     schm
    -0.07
    POSITIVE LOGITS
     ende
    0.08
     achten
    0.07
    alking
    0.07
    lsl
    0.07
    ensaje
    0.07
    awu
    0.07
    iru
    0.07
     ukuya
    0.07
     u
    0.07
     razvoj
    0.07
    Activations Density 0.266%

    No Known Activations