© 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. 79427
    Prev
    Next
    INDEX
    Explanations

    Random text

    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
    Julia
    -0.08
    Mein
    -0.07
     hyperlinks
    -0.07
    /reference
    -0.07
    arching
    -0.07
    μι
    -0.07
    ্ৰী
    -0.07
    治
    -0.07
    verb
    -0.07
    दा
    -0.07
    POSITIVE LOGITS
     చిన్న
    0.15
     ছোট
    0.14
     küçük
    0.13
     الحجم
    0.13
     الصغيرة
    0.12
     નાના
    0.12
    小
    0.12
    、小
    0.12
     小
    0.12
    “小
    0.12
    Activations Density 0.393%

    No Known Activations