© 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. 94624
    Prev
    Next
    INDEX
    Explanations

    Acceptance/selectivity

    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
     polyurethane
    -0.08
     法
    -0.08
     الفور
    -0.07
    পুর
    -0.07
    لي
    -0.07
     خطة
    -0.07
     Lager
    -0.07
     resin
    -0.07
     accumulate
    -0.07
     translation
    -0.07
    POSITIVE LOGITS
     ежеднев
    0.09
     diariamente
    0.09
     ежедневно
    0.09
    _daily
    0.09
     कठिन
    0.09
    ifficulty
    0.08
    每日
    0.08
     어렵
    0.08
     दैनिक
    0.08
     высок
    0.08
    Activations Density 0.009%

    No Known Activations