© 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. 79420
    Prev
    Next
    INDEX
    Explanations

    latter

    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
     takeover
    -0.09
     sen
    -0.07
    _the
    -0.07
    rnd
    -0.07
     sam
    -0.07
     हे
    -0.07
    AIN
    -0.07
     tossed
    -0.07
     temper
    -0.07
     nervous
    -0.07
    POSITIVE LOGITS
    forth
    0.09
     Fitzgerald
    0.08
     contrat
    0.08
     Obl
    0.08
    uy
    0.07
     obl
    0.07
    bums
    0.07
     Fel
    0.07
    zuf
    0.07
     Ludwig
    0.07
    Activations Density 0.004%

    No Known Activations