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. 88151
    Prev
    Next
    INDEX
    Explanations

    image generation prompts

    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
     probable
    -0.08
     justa
    -0.08
     shards
    -0.07
    -found
    -0.07
     accessed
    -0.07
    性质
    -0.07
    概率
    -0.07
    Leak
    -0.07
     meas
    -0.07
    agana
    -0.07
    POSITIVE LOGITS
     ઉપરાંત
    0.09
                                                                    
    0.09
     Bonus
    0.08
     Mediterr
    0.08
    bonus
    0.08
     umfang
    0.08
     Ruiz
    0.07
    rell
    0.07
     Abdul
    0.07
     erweitert
    0.07
    Activations Density 0.003%

    No Known Activations