© 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. 3-RESID-POST-AA
    11. 13175
    Prev
    Next
    INDEX
    Explanations

    及时

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Vid
    -0.09
     IDX
    -0.07
     Fitch
    -0.07
    vid
    -0.07
    wür
    -0.07
     fungi
    -0.07
     Vid
    -0.07
    ído
    -0.07
     elegance
    -0.07
    弹
    -0.07
    POSITIVE LOGITS
    _corr
    0.08
     Workplace
    0.08
     intangible
    0.08
     Grat
    0.07
     Kay
    0.07
     plum
    0.07
     Corr
    0.07
    čin
    0.07
     Lá
    0.07
     malad
    0.07
    Activations Density 0.003%

    No Known Activations