© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 50778
    Prev
    Next
    INDEX
    Explanations

    chat

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    日志
    -0.08
     logged
    -0.08
    ，因此
    -0.08
     Logo
    -0.08
    Logger
    -0.08
    _Post
    -0.08
    _Log
    -0.08
    所谓
    -0.07
    egin
    -0.07
    аг
    -0.07
    POSITIVE LOGITS
     F
    0.08
     retailers
    0.08
     fá
    0.08
    -extension
    0.08
     waarmee
    0.08
     neem
    0.08
     extensions
    0.08
     연구
    0.08
     Extensions
    0.07
    -sales
    0.07
    Activations Density 0.004%

    No Known Activations