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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 64621
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    而言
    -0.09
     ক্ষেত্রে
    -0.09
    来说
    -0.08
    RES
    -0.08
     RES
    -0.07
    িকে
    -0.07
     শব্দ
    -0.07
    ，而且
    -0.07
    SY
    -0.07
    gre
    -0.07
    POSITIVE LOGITS
     turb
    0.08
     Bach
    0.08
     Attr
    0.08
     Tai
    0.07
    шел
    0.07
     Fl
    0.07
     Lamp
    0.07
    bios
    0.07
    owment
    0.07
     evidenced
    0.07
    Activations Density 0.102%

    No Known Activations