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. 112291
    Prev
    Next
    INDEX
    Explanations

    Prompt creation instructions

    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
     얻
    -0.08
     શકે
    -0.08
     Formular
    -0.08
     능
    -0.08
     Polyester
    -0.08
     tres
    -0.07
    ıs
    -0.07
    astic
    -0.07
     offenses
    -0.07
    arget
    -0.07
    POSITIVE LOGITS
     lush
    0.09
     tropical
    0.09
     lumineux
    0.09
     nostalgic
    0.09
     sombre
    0.09
     glowing
    0.09
     色
    0.09
     ambience
    0.09
     बारिश
    0.09
    夜
    0.09
    Activations Density 0.003%

    No Known Activations