© 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. 129083
    Prev
    Next
    INDEX
    Explanations

    OW

    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
     직원
    -0.08
     employees
    -0.08
    ích
    -0.08
    pets
    -0.08
     לע
    -0.07
     مصالح
    -0.07
    757
    -0.07
     toxins
    -0.07
     werknemers
    -0.07
     freisin
    -0.07
    POSITIVE LOGITS
     coexist
    0.08
     Bun
    0.07
     siste
    0.07
    üc
    0.07
    swer
    0.07
    stum
    0.07
    ,j
    0.07
    Assessment
    0.07
     Fac
    0.07
     перес
    0.07
    Activations Density 0.000%

    No Known Activations