© 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. 103466
    Prev
    Next
    INDEX
    Explanations

    discuss and related words

    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
     ensured
    -0.09
     kuni
    -0.09
     προσπά
    -0.09
     trato
    -0.09
     preferably
    -0.09
     cuánto
    -0.08
     ought
    -0.08
     પ્રયાસ
    -0.08
     tratando
    -0.08
     చేస
    -0.08
    POSITIVE LOGITS
     Discuss
    0.13
     discuss
    0.13
    Discuss
    0.13
     discutir
    0.11
     discussing
    0.10
     bespreken
    0.10
     discuter
    0.10
     discusses
    0.09
     bespre
    0.09
    讨论
    0.09
    Activations Density 0.004%

    No Known Activations