© 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. 95544
    Prev
    Next
    INDEX
    Explanations

    ync

    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
    安
    -0.08
    宇
    -0.08
    艾
    -0.07
    _O
    -0.07
     indications
    -0.07
     trés
    -0.07
    _Dep
    -0.07
    �
    -0.07
    天
    -0.07
    纪律
    -0.07
    POSITIVE LOGITS
     cares
    0.08
     shortcuts
    0.08
    등
    0.08
    /end
    0.07
    ")},↵
    0.07
     परिच
    0.07
     puissant
    0.07
    Ped
    0.07
     vcs
    0.07
    :VC
    0.07
    Activations Density 0.001%

    No Known Activations