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. 65831
    Prev
    Next
    INDEX
    Explanations

    time, event

    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
     прир
    -0.08
     вак
    -0.08
     свай
    -0.08
     :)
    -0.08
    Cob
    -0.08
     feestje
    -0.08
     literally
    -0.07
     הקר
    -0.07
     собой
    -0.07
     autant
    -0.07
    POSITIVE LOGITS
     ayrıca
    0.10
    その他
    0.09
    udover
    0.09
    交
    0.08
     এছ
    0.08
     importantly
    0.08
     lastly
    0.08
     その他
    0.08
    辅助
    0.07
    还有
    0.07
    Activations Density 0.246%

    No Known Activations