© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 113122
    Prev
    Next
    INDEX
    Explanations

    the

    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
    .system
    -0.08
     system
    -0.08
     resource
    -0.08
    'installation
    -0.08
    <Resource
    -0.07
    Resource
    -0.07
    igns
    -0.07
     संस
    -0.07
    system
    -0.07
    _SYSTEM
    -0.07
    POSITIVE LOGITS
     hollow
    0.12
     interiors
    0.11
     intérieure
    0.11
    Interior
    0.10
     interior
    0.10
     Interiors
    0.10
     sandwich
    0.10
     الوسط
    0.09
     Middle
    0.09
     Interior
    0.09
    Activations Density 0.016%

    No Known Activations