© 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. 44393
    Prev
    Next
    INDEX
    Explanations

    maximum value in sequence

    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
    -bind
    -0.09
     स्लॉट
    -0.09
     معدات
    -0.08
     التواصل
    -0.08
     �
    -0.08
     EV
    -0.08
     الأجهزة
    -0.08
     पहन
    -0.08
     AWS
    -0.08
    Resp
    -0.08
    POSITIVE LOGITS
     Negative
    0.10
     parado
    0.10
     negativity
    0.10
    negative
    0.09
     negative
    0.09
     negatif
    0.09
    停止
    0.09
     negativo
    0.09
     paradox
    0.09
    til
    0.09
    Activations Density 0.017%

    No Known Activations