© 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. 79146
    Prev
    Next
    INDEX
    Explanations

    VPN

    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
     bron
    -0.08
    문화
    -0.07
     cuisson
    -0.07
     Lisp
    -0.07
     pastries
    -0.07
     pottery
    -0.07
    gli
    -0.07
     deeds
    -0.07
     pedestrians
    -0.07
     legislature
    -0.07
    POSITIVE LOGITS
     VPN
    0.09
     службу
    0.09
    feren
    0.08
    етер
    0.08
    _fl
    0.08
    ;;↵
    0.08
     princip
    0.08
    dienst
    0.08
     Direkt
    0.07
     vpn
    0.07
    Activations Density 0.003%

    No Known Activations