© 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. 3-RESID-POST-AA
    11. 13127
    Prev
    Next
    INDEX
    Explanations

    у

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Adu
    -0.08
     Carter
    -0.08
     mulig
    -0.08
     brace
    -0.07
    Cust
    -0.07
    ்ம
    -0.07
    _put
    -0.07
    psi
    -0.07
     сүй
    -0.07
     kink
    -0.07
    POSITIVE LOGITS
     dip
    0.08
    597
    0.07
     oat
    0.07
    wine
    0.07
     하나
    0.07
    宗
    0.07
     Warren
    0.07
    prow
    0.07
    quist
    0.07
     Kenn
    0.07
    Activations Density 0.001%

    No Known Activations