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. 88165
    Prev
    Next
    INDEX
    Explanations

    too

    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
     prospect
    -0.08
     AZ
    -0.08
    orks
    -0.07
     ondersteunt
    -0.07
     RO
    -0.07
    -0.07
     pros
    -0.07
     Ro
    -0.07
     roast
    -0.07
    lets
    -0.07
    POSITIVE LOGITS
     слишком
    0.10
     simplistic
    0.09
    突然
    0.09
        
    ↵    
    ↵
    0.09
     alsof
    0.09
     nepot
    0.09
     liian
    0.09
     langwe
    0.09
    مانية
    0.09
     superfic
    0.08
    Activations Density 0.013%

    No Known Activations