© 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. 31134
    Prev
    Next
    INDEX
    Explanations

    math

    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
    ============
    -0.08
     sebenarnya
    -0.08
     divulgado
    -0.08
     Hoe
    -0.07
    ============↵
    -0.07
    ავს
    -0.07
    ေပး
    -0.07
     indirectly
    -0.07
     أعلن
    -0.07
     __
    -0.07
    POSITIVE LOGITS
     которого
    0.08
    _es
    0.07
    可是
    0.07
    anç
    0.07
    篇
    0.07
    ਕਾਰ
    0.07
    ¥
    0.07
     indict
    0.07
     masculina
    0.07
    옵
    0.07
    Activations Density 0.103%

    No Known Activations