© 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. 19-RESID-POST-AA
    11. 102242
    Prev
    Next
    INDEX
    Explanations

    email

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fascinated
    -0.09
     histórias
    -0.09
     Werke
    -0.09
     Geschichten
    -0.08
     যুগ
    -0.08
     histoires
    -0.08
     panoramic
    -0.08
     voyeur
    -0.08
     Literatura
    -0.08
     살아
    -0.08
    POSITIVE LOGITS
     courteous
    0.18
     politely
    0.17
     notifying
    0.17
     polite
    0.17
    邮件
    0.16
    通知
    0.16
     höf
    0.16
     email
    0.15
     professionalism
    0.15
     уведом
    0.15
    Activations Density 0.055%

    No Known Activations