Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 58554
    Prev
    Next
    INDEX
    Explanations

    6

    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
    ,实现
    -0.08
    (xml
    -0.08
    风险
    -0.08
    পূর্ণ
    -0.08
     fulfilling
    -0.08
    储
    -0.07
    воз
    -0.07
    发挥
    -0.07
    泄
    -0.07
     fulfillment
    -0.07
    POSITIVE LOGITS
     pretrained
    0.08
    нащ
    0.08
     Intelligent
    0.08
     grapp
    0.07
    Advanced
    0.07
     newest
    0.07
     več
    0.07
     newer
    0.07
     వద్ద
    0.07
     Tower
    0.07
    Activations Density 0.009%

    No Known Activations