© 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. 45455
    Prev
    Next
    INDEX
    Explanations

    lop

    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
    _bn
    -0.08
     teve
    -0.08
    ,re
    -0.08
     inc
    -0.08
    _reward
    -0.07
     bek
    -0.07
     patr
    -0.07
    愿
    -0.07
     who's
    -0.07
     Macedonia
    -0.07
    POSITIVE LOGITS
     inhibits
    0.11
     inhibit
    0.10
     inhibition
    0.10
     inhibitory
    0.10
     prohibits
    0.09
     inhib
    0.09
    hibition
    0.08
     tó
    0.08
     influence
    0.08
     regulate
    0.08
    Activations Density 0.004%

    No Known Activations