© 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. 15-RESID-POST-AA
    11. 16488
    Prev
    Next
    INDEX
    Explanations

    books and publications

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     работать
    -0.09
    ethers
    -0.09
    уществ
    -0.08
    Other
    -0.08
    거나
    -0.08
    crear
    -0.07
    other
    -0.07
     ():
    -0.07
     empezó
    -0.07
     (£
    -0.07
    POSITIVE LOGITS
     أهمية
    0.09
     طريقة
    0.08
    ريقية
    0.08
    وأوضح
    0.08
     hōʻike
    0.08
    ირვ
    0.08
     qualitative
    0.08
    وأشار
    0.08
    ირდა
    0.08
     تقول
    0.08
    Activations Density 0.037%

    No Known Activations