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. 114118
    Prev
    Next
    INDEX
    Explanations

    exactly

    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
    出来
    -0.08
    عمال
    -0.07
    -пр
    -0.07
     yaitu
    -0.07
    יצד
    -0.07
     Edwin
    -0.07
     redor
    -0.07
     Editors
    -0.07
     буду
    -0.07
     zwar
    -0.07
    POSITIVE LOGITS
     hein
    0.09
     antis
    0.08
     nonexistent
    0.08
     socialism
    0.08
    unable
    0.08
     provid
    0.07
    �
    0.07
     susceptibles
    0.07
    大道
    0.07
     tồn
    0.07
    Activations Density 0.007%

    No Known Activations