© 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. 13162
    Prev
    Next
    INDEX
    Explanations

    характеристи

    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
     pega
    -0.08
    359
    -0.07
     imaginable
    -0.07
     tank
    -0.07
     imperial
    -0.07
    -brand
    -0.06
     Club
    -0.06
    026
    -0.06
     ham
    -0.06
     pegar
    -0.06
    POSITIVE LOGITS
    Mov
    0.08
     ra
    0.08
    涵
    0.08
     sche
    0.08
     PCs
    0.07
    �
    0.07
     radios
    0.07
     Santana
    0.07
    端
    0.07
    Chinese
    0.07
    Activations Density 0.003%

    No Known Activations