Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 98533
    Prev
    Next
    INDEX
    Explanations

    services in different languages

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rebellion
    -0.08
     rebel
    -0.08
     loot
    -0.07
     debates
    -0.07
     मतदान
    -0.07
    vote
    -0.07
     पुल
    -0.07
    奋斗
    -0.07
     rebellious
    -0.07
     genoc
    -0.07
    POSITIVE LOGITS
     خدمات
    0.25
     സേവ
    0.24
     서비스를
    0.23
     Dienstleistungen
    0.23
     услуги
    0.23
     услуг
    0.23
     services
    0.22
     서비스
    0.22
     layanan
    0.22
    サービス
    0.22
    Activations Density 0.495%

    No Known Activations