© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 68669
    Prev
    Next
    INDEX
    Explanations

    Voila

    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
     específicamente
    -0.08
     specifically
    -0.08
     overtime
    -0.08
     verkeerde
    -0.08
    ங்களில்
    -0.07
    $return
    -0.07
     espe
    -0.07
     especificamente
    -0.07
     linn
    -0.07
     vork
    -0.07
    POSITIVE LOGITS
     voila
    0.16
    Voilà
    0.14
     voilà
    0.13
    即可
    0.13
     Voilà
    0.12
     listo
    0.12
    Ready
    0.11
     selesai
    0.11
     ready
    0.11
    ready
    0.11
    Activations Density 0.101%

    No Known Activations