© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 65407
    Prev
    Next
    INDEX
    Explanations

    of

    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
     peur
    -0.08
    Clone
    -0.08
    Filters
    -0.08
     clon
    -0.08
    分钱
    -0.08
     cloning
    -0.08
    .filters
    -0.08
     freel
    -0.08
     toxin
    -0.08
     phân
    -0.08
    POSITIVE LOGITS
     ملاقات
    0.11
     speeches
    0.10
    习近平
    0.10
     زيارة
    0.09
    外交
    0.09
     Reuters
    0.09
     rhetoric
    0.09
     briefing
    0.09
     Putin
    0.09
     సమావేశ
    0.09
    Activations Density 0.120%

    No Known Activations