© 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. 108223
    Prev
    Next
    INDEX
    Explanations

    checking on customers

    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
     impe
    -0.08
     St
    -0.08
     类型
    -0.08
    类型
    -0.08
    usti
    -0.08
    St
    -0.08
    特点
    -0.07
     typisch
    -0.07
     특징
    -0.07
     sorting
    -0.07
    POSITIVE LOGITS
     outreach
    0.11
     Outreach
    0.10
     xyuas
    0.10
     консульт
    0.09
     hafi
    0.09
     સંપર્ક
    0.09
    询
    0.09
    Check
    0.09
    очку
    0.09
     acompanhamento
    0.09
    Activations Density 0.033%

    No Known Activations