© 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. 19-RESID-POST-AA
    11. 102542
    Prev
    Next
    INDEX
    Explanations

    size comparisons

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kvæmt
    -0.09
    kið
    -0.09
     hästi
    -0.09
     diversos
    -0.08
     foarte
    -0.08
    mbled
    -0.08
    ņas
    -0.08
     rất
    -0.08
     kiiresti
    -0.08
     quick
    -0.08
    POSITIVE LOGITS
     smaller
    0.29
     larger
    0.28
     lower
    0.24
     higher
    0.24
     lesser
    0.23
     Smaller
    0.22
     größere
    0.22
     höhere
    0.22
     groter
    0.22
     Larger
    0.21
    Activations Density 0.092%

    No Known Activations