© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 68377
    Prev
    Next
    INDEX
    Explanations

    ibal

    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
    ाउंट
    -0.08
    فت
    -0.08
     gey
    -0.07
    psilon
    -0.07
    伊
    -0.07
     glide
    -0.07
     quais
    -0.07
     lava
    -0.07
    passed
    -0.07
     bubbles
    -0.07
    POSITIVE LOGITS
     Malawi
    0.08
    ajana
    0.08
     Berger
    0.08
     (!)
    0.08
     Jian
    0.08
    christ
    0.07
    0.07
     komun
    0.07
     গ্রহণ
    0.07
     Chau
    0.07
    Activations Density 0.003%

    No Known Activations