© 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. 25867
    Prev
    Next
    INDEX
    Explanations

    Chinese character 字

    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
     impotence
    -0.09
     LAP
    -0.08
     GENERAL
    -0.08
     rigidity
    -0.08
     কোথ
    -0.08
    显
    -0.08
    _jump
    -0.08
     DEN
    -0.08
    ью
    -0.08
    кер
    -0.07
    POSITIVE LOGITS
     counting
    0.09
     count
    0.08
     contador
    0.08
    (count
    0.08
    ਆਂ
    0.08
     counted
    0.07
    ,'
    0.07
     Forum
    0.07
     Counting
    0.07
    ATM
    0.07
    Activations Density 0.006%

    No Known Activations