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. 58171
    Prev
    Next
    INDEX
    Explanations

    Foreign languages phrases

    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
     이에
    -0.08
     Millennium
    -0.08
     ख़
    -0.08
     hiermee
    -0.08
    (action
    -0.08
     spéc
    -0.08
     동시에
    -0.08
     satisfait
    -0.08
     conform
    -0.07
    می
    -0.07
    POSITIVE LOGITS
     aumenta
    0.08
    achten
    0.08
    0.08
     gd
    0.07
    ga
    0.07
     Odessa
    0.07
     Maintenance
    0.07
     Stella
    0.07
     Increase
    0.07
     maintenance
    0.07
    Activations Density 0.001%

    No Known Activations