© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 113159
    Prev
    Next
    INDEX
    Explanations

    视

    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
     fences
    -0.07
    -
    -0.07
    (Constant
    -0.07
    .shortcuts
    -0.07
     collects
    -0.07
     丁
    -0.07
     وأن
    -0.07
     PL
    -0.07
     Saturdays
    -0.07
    _red
    -0.07
    POSITIVE LOGITS
    情况
    0.11
     deemed
    0.10
     Depends
    0.10
     depends
    0.09
     esigenze
    0.09
     Bedarf
    0.09
     necessidades
    0.09
     kebutuhan
    0.09
    depends
    0.09
    Depends
    0.09
    Activations Density 0.029%

    No Known Activations