© 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. 54408
    Prev
    Next
    INDEX
    Explanations

    signs

    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
     exploited
    -0.08
    927
    -0.08
     Costs
    -0.08
     Kosten
    -0.08
     희
    -0.07
     Ingen
    -0.07
     coûts
    -0.07
    Donc
    -0.07
     ఎవ
    -0.07
     Donc
    -0.07
    POSITIVE LOGITS
     punctuation
    0.10
     emojis
    0.09
     peppers
    0.09
     traditional
    0.09
     literal
    0.08
     verbal
    0.08
     keyword
    0.08
     refers
    0.08
     b
    0.08
     pacing
    0.08
    Activations Density 0.009%

    No Known Activations