© 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. 16643
    Prev
    Next
    INDEX
    Explanations

    of

    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
    uele
    -0.07
     bü
    -0.07
     chví
    -0.07
    agd
    -0.07
    限定
    -0.07
    Mom
    -0.07
     Wishes
    -0.07
    bene
    -0.07
     Fant
    -0.07
    limited
    -0.07
    POSITIVE LOGITS
     различных
    0.15
     various
    0.15
     المختلفة
    0.14
     विभिन्न
    0.14
     olika
    0.14
     разных
    0.14
    各种
    0.14
     berbagai
    0.14
     ulike
    0.14
     różnych
    0.13
    Activations Density 0.026%

    No Known Activations