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. 78536
    Prev
    Next
    INDEX
    Explanations

    Use

    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
     anderes
    -0.09
    DEV
    -0.08
                                      
    -0.08
     DEV
    -0.08
    Maybe
    -0.08
    Interesting
    -0.08
     bonnes
    -0.08
     GOOD
    -0.07
                          
    -0.07
    -other
    -0.07
    POSITIVE LOGITS
     here's
    0.08
     gant
    0.08
    kot
    0.08
     secret
    0.07
    arre
    0.07
     sweeping
    0.07
    ARC
    0.07
     SEPT
    0.07
     Secret
    0.07
    Sek
    0.07
    Activations Density 0.169%

    No Known Activations