© 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. 19-RESID-POST-AA
    11. 102557
    Prev
    Next
    INDEX
    Explanations

    How

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     někter
    -0.08
     They'll
    -0.08
     করছে
    -0.08
     કેટલીક
    -0.08
     snel
    -0.08
     devrait
    -0.07
     két
    -0.07
     algunas
    -0.07
     nuestro
    -0.07
     We'll
    -0.07
    POSITIVE LOGITS
     당시
    0.12
     afterward
    0.11
     итоге
    0.10
     обстоятель
    0.10
     afterwards
    0.10
     subsequent
    0.09
     eventual
    0.09
     उस
    0.09
     fue
    0.09
     damal
    0.09
    Activations Density 0.012%

    No Known Activations