© 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. 108209
    Prev
    Next
    INDEX
    Explanations

    research publications

    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
     Clubs
    -0.11
     Pew
    -0.09
     Celebrity
    -0.09
     newspapers
    -0.09
     celebrities
    -0.09
     Playboy
    -0.09
     Patrol
    -0.09
     homosexuality
    -0.09
     televis
    -0.09
     campsite
    -0.09
    POSITIVE LOGITS
     Computational
    0.09
    Engineering
    0.09
     collaborators
    0.09
     colleagues
    0.09
     engineering
    0.09
     neuroscience
    0.09
     engineers
    0.09
     müh
    0.08
    IBM
    0.08
     computational
    0.08
    Activations Density 0.065%

    No Known Activations