© 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. 99755
    Prev
    Next
    INDEX
    Explanations

    Mixed languages, instructions

    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
    进去
    -0.08
    ittle
    -0.08
    Mess
    -0.08
    -0.08
    Ml
    -0.08
    Austr
    -0.08
    Univers
    -0.08
     turbul
    -0.08
     Österreich
    -0.07
    *x
    -0.07
    POSITIVE LOGITS
     답
    0.11
     उत्तर
    0.11
     antwort
    0.11
     ઉત્તર
    0.10
    回答
    0.10
     answer
    0.10
     ಉತ್ತರ
    0.10
     ответы
    0.10
     উত্তর
    0.10
    उत्तर
    0.10
    Activations Density 0.162%

    No Known Activations