© 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. 113596
    Prev
    Next
    INDEX
    Explanations

    copyright symbol

    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
     kapcsolat
    -0.09
     boek
    -0.08
     bolan
    -0.08
    calar
    -0.08
     buffer
    -0.08
    (buffer
    -0.08
     бос
    -0.07
    ，与
    -0.07
     buchen
    -0.07
    кия
    -0.07
    POSITIVE LOGITS
    版权
    0.10
     Copyright
    0.10
    Copyright
    0.09
     copyrights
    0.09
     copyright
    0.09
    copyright
    0.09
    opyright
    0.08
     legally
    0.08
     lawful
    0.08
    META
    0.08
    Activations Density 0.009%

    No Known Activations