© 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. 29121
    Prev
    Next
    INDEX
    Explanations

    configuration

    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
     Clayton
    -0.09
     mães
    -0.08
     madres
    -0.08
     hookup
    -0.08
     gj
    -0.08
     marin
    -0.07
    妈妈
    -0.07
     mast
    -0.07
     ausgest
    -0.07
     perfekte
    -0.07
    POSITIVE LOGITS
     MMORPG
    0.09
     databases
    0.08
    deployment
    0.08
     deployments
    0.08
    sible
    0.08
    Deployment
    0.08
     tlhal
    0.08
    /software
    0.08
     manuals
    0.08
     servers
    0.08
    Activations Density 0.008%

    No Known Activations