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. 45122
    Prev
    Next
    INDEX
    Explanations

    captivating

    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
    roof
    -0.08
    idem
    -0.08
     కన
    -0.08
     Sinai
    -0.08
    alance
    -0.07
    oko
    -0.07
    rial
    -0.07
    ಲಾಗ
    -0.07
     tätä
    -0.07
     fascia
    -0.07
    POSITIVE LOGITS
     Judges
    0.08
     подоб
    0.07
     Advancement
    0.07
     abduct
    0.07
     Kevin
    0.07
    <B
    0.07
     Similar
    0.07
     Benny
    0.07
     Hum
    0.07
     Scorpio
    0.07
    Activations Density 0.006%

    No Known Activations