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. 26778
    Prev
    Next
    INDEX
    Explanations

    influence

    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
     playful
    -0.08
     wool
    -0.08
    &p
    -0.08
     Nou
    -0.08
     Plastic
    -0.07
     personalities
    -0.07
     nou
    -0.07
     Gotham
    -0.07
     lifespan
    -0.07
     Eureka
    -0.07
    POSITIVE LOGITS
     dirigir
    0.08
     শুন
    0.08
     পরীক্ষ
    0.08
     ilo
    0.08
     যুক্ত
    0.08
    ysen
    0.08
    �
    0.08
     DUI
    0.08
     har
    0.08
    affirm
    0.08
    Activations Density 0.005%

    No Known Activations