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. 29910
    Prev
    Next
    INDEX
    Explanations

    /in

    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
     Straw
    -0.08
     Textile
    -0.08
     Tire
    -0.08
    ikwa
    -0.07
    atin
    -0.07
     fulfill
    -0.07
     Sama
    -0.07
     monit
    -0.07
     Tough
    -0.07
     decompress
    -0.07
    POSITIVE LOGITS
     
    0.08
    �
    0.08
    ­
    0.08
    傅
    0.08
     Amal
    0.08
     başlayan
    0.08
     gotovo
    0.08
     emotion
    0.08
     emoties
    0.07
     adrenaline
    0.07
    Activations Density 0.000%

    No Known Activations