© 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. 19-RESID-POST-AA
    11. 102863
    Prev
    Next
    INDEX
    Explanations

    optional

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ización
    -0.10
     婷
    -0.09
     简
    -0.09
     日日
    -0.08
     日韩
    -0.08
     国产
    -0.08
     �
    -0.08
     遂
    -0.08
      
    -0.08
    ･･
    -0.08
    POSITIVE LOGITS
    .
    0.11
    .By
    0.10
    (old
    0.08
    (original
    0.08
    (System
    0.08
    (default
    0.08
    (answer
    0.08
    。当
    0.08
    Army
    0.08
    .The
    0.08
    Activations Density 0.000%

    No Known Activations