© 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. 11-RESID-POST-AA
    11. 118
    Prev
    Next
    INDEX
    Explanations

    dog training

    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
     Rechnung
    -0.10
    签到
    -0.09
    新闻网
    -0.09
    金额
    -0.09
    彩票平台
    -0.09
    官方下载
    -0.08
    总书记
    -0.08
    ্তা
    -0.08
     congressional
    -0.08
    .entities
    -0.08
    POSITIVE LOGITS
     प्रशिक्षण
    0.10
    training
    0.09
     temperament
    0.09
    	setup
    0.09
     treinamento
    0.09
     сексу
    0.09
     behavioral
    0.09
     parenting
    0.09
    습
    0.09
     troubleshooting
    0.09
    Activations Density 0.022%

    No Known Activations