© 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. 45726
    Prev
    Next
    INDEX
    Explanations

    is

    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
    贯彻
    -0.08
    loge
    -0.08
     বাজার
    -0.07
     SQLException
    -0.07
     eased
    -0.07
    781
    -0.07
     ierr
    -0.07
    ਾਨ
    -0.07
    ergency
    -0.07
     seismic
    -0.07
    POSITIVE LOGITS
    年龄
    0.12
     infantil
    0.11
     leeftijd
    0.11
     fantasies
    0.11
     فتاة
    0.10
     ages
    0.10
     âge
    0.10
     edad
    0.10
    adult
    0.10
    儿童
    0.10
    Activations Density 0.021%

    No Known Activations