© 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. 91576
    Prev
    Next
    INDEX
    Explanations

    meal

    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
    _domain
    -0.08
     domain
    -0.08
    召开
    -0.07
     informasjon
    -0.07
    ాటి
    -0.07
    -domain
    -0.07
    ographique
    -0.07
     जारी
    -0.07
     zid
    -0.07
    .portlet
    -0.07
    POSITIVE LOGITS
     breakfasts
    0.09
    sexual
    0.08
     whopping
    0.08
     abwechslungs
    0.08
     prepping
    0.08
    аму
    0.08
    Repeat
    0.08
     stocked
    0.08
    mor
    0.07
    養
    0.07
    Activations Density 0.010%

    No Known Activations