© 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. 97422
    Prev
    Next
    INDEX
    Explanations

    уч

    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
    าหน
    -0.07
     perceive
    -0.07
     분석
    -0.07
    �
    -0.07
     рах
    -0.07
    იც
    -0.07
    ورد
    -0.07
    切
    -0.07
    拔
    -0.07
    ώσεις
    -0.07
    POSITIVE LOGITS
    ителем
    0.11
    ителю
    0.11
    ителей
    0.11
    нями
    0.11
    ителя
    0.11
    erst
    0.10
    итель
    0.10
    есть
    0.10
    ząc
    0.09
    িনী
    0.09
    Activations Density 0.002%

    No Known Activations