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. 588
    Prev
    Next
    INDEX
    Explanations

    Title

    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
     Pepe
    -0.08
    后来
    -0.08
    erz
    -0.08
     보면
    -0.08
    shwa
    -0.07
    Hyper
    -0.07
    urun
    -0.07
     中天
    -0.07
     moni
    -0.07
    xff
    -0.07
    POSITIVE LOGITS
    主题
    0.08
    하도록
    0.08
    합니다
    0.07
    할
    0.07
    天气
    0.07
     блока
    0.07
     renew
    0.07
     Equals
    0.07
    입니다
    0.07
    leine
    0.07
    Activations Density 0.028%

    No Known Activations