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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 48630
    Prev
    Next
    INDEX
    Explanations

    service

    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
     services
    -0.24
    服务
    -0.24
    サービス
    -0.24
     layanan
    -0.24
     servici
    -0.23
     servizio
    -0.23
     servicio
    -0.23
     serviço
    -0.23
     서비스
    -0.23
    _service
    -0.22
    POSITIVE LOGITS
     rendered
    0.11
    _render
    0.10
    renders
    0.10
     Render
    0.10
     rendu
    0.10
    render
    0.09
    Render
    0.09
     renders
    0.09
    ింగ
    0.09
    (render
    0.09
    Activations Density 0.020%

    No Known Activations