© 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. 129197
    Prev
    Next
    INDEX
    Explanations

    childcare

    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
    innitus
    -0.08
    ystems
    -0.08
    _shipping
    -0.08
    553
    -0.08
     burocr
    -0.07
     electrón
    -0.07
     mutations
    -0.07
     类型
    -0.07
     hometown
    -0.07
     tinnitus
    -0.07
    POSITIVE LOGITS
     सभा
    0.09
     massacre
    0.09
    éricaine
    0.09
    huma
    0.08
    ev
    0.08
    evas
    0.08
    #define
    0.08
     liebe
    0.08
     tror
    0.08
     accueill
    0.08
    Activations Density 0.028%

    No Known Activations