© 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. 91610
    Prev
    Next
    INDEX
    Explanations

    mandates

    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
     kakhulu
    -0.08
    inon
    -0.07
    br
    -0.07
     পরিচাল
    -0.07
     allotted
    -0.07
     Carte
    -0.07
     escort
    -0.07
    xes
    -0.07
     Gand
    -0.07
    alter
    -0.07
    POSITIVE LOGITS
    -faced
    0.08
     viš
    0.08
     grit
    0.08
     AT
    0.08
    ỳ
    0.07
     ví
    0.07
    ੱਖ
    0.07
    очек
    0.07
     Reading
    0.07
     Elem
    0.07
    Activations Density 0.065%

    No Known Activations