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. 49778
    Prev
    Next
    INDEX
    Explanations

    he

    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
    ervers
    -0.09
    خانه
    -0.08
    чак
    -0.08
     ở
    -0.08
    543
    -0.08
    сар
    -0.08
     सिक
    -0.08
    143
    -0.08
    財布
    -0.08
    444
    -0.07
    POSITIVE LOGITS
    浓
    0.11
     dill
    0.09
     molho
    0.08
     hưởng
    0.08
     moon
    0.08
    欢乐
    0.07
    露
    0.07
     التاريخ
    0.07
     BBQ
    0.07
     marine
    0.07
    Activations Density 0.020%

    No Known Activations