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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 8883
    Prev
    Next
    INDEX
    Explanations

    thread

    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
     Thy
    -0.08
     Qo
    -0.08
     Shrine
    -0.07
    ்�
    -0.07
     تقييم
    -0.07
    評
    -0.07
     Sociedad
    -0.07
     OB
    -0.07
     평가
    -0.07
     Beer
    -0.07
    POSITIVE LOGITS
    (wallet
    0.10
     америка
    0.10
    文章
    0.09
     ғына
    0.09
     кенә
    0.09
     امریکا
    0.09
    钱怎么
    0.09
    账
    0.09
     sveitar
    0.09
    .ethereum
    0.09
    Activations Density 0.028%

    No Known Activations