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. 117291
    Prev
    Next
    INDEX
    Explanations

    herself

    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
    _income
    -0.07
     lamp
    -0.07
    -notch
    -0.07
    -eng
    -0.07
     clearly
    -0.07
     lap
    -0.07
     fich
    -0.07
     inov
    -0.07
     madu
    -0.06
     май
    -0.06
    POSITIVE LOGITS
     saiu
    0.09
     uống
    0.08
    済
    0.08
    疾
    0.07
     draußen
    0.07
    ättä
    0.07
     싸
    0.07
    Сп
    0.07
    卫
    0.07
    韩国
    0.07
    Activations Density 0.000%

    No Known Activations