© 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. 68487
    Prev
    Next
    INDEX
    Explanations

    Experiments

    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
     appreci
    -0.09
    ട
    -0.08
     cert
    -0.07
    ဇ
    -0.07
     sensit
    -0.07
     sens
    -0.07
    VED
    -0.07
    SERVICE
    -0.07
    লায়
    -0.07
     service
    -0.07
    POSITIVE LOGITS
     진행
    0.10
     إجراء
    0.10
     durchführen
    0.09
     conducted
    0.09
     durchgeführt
    0.09
     التج
    0.09
     القيام
    0.09
     முய
    0.08
     conducting
    0.08
     Conduct
    0.08
    Activations Density 0.013%

    No Known Activations