© 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. 11-RESID-POST-AA
    11. 111394
    Prev
    Next
    INDEX
    Explanations

    通过

    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
     Todos
    -0.08
    izado
    -0.08
    �
    -0.08
     vegetal
    -0.07
     handi
    -0.07
    -ios
    -0.07
    Todos
    -0.07
     asi
    -0.07
    etsa
    -0.07
     <--
    -0.07
    POSITIVE LOGITS
     ner
    0.08
     Southeastern
    0.08
     جدول
    0.08
     توفير
    0.08
     чего
    0.07
    调整
    0.07
    _raise
    0.07
     similarities
    0.07
    上述
    0.07
    �
    0.07
    Activations Density 0.009%

    No Known Activations