© 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 EvalsExportsinterp-engineNEWAPI 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. 70096
    Prev
    Next
    INDEX
    Explanations

    wait

    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
     don
    -0.08
     soc
    -0.08
    ذا
    -0.08
     jo
    -0.08
     deste
    -0.08
    pathy
    -0.07
     fod
    -0.07
     thr
    -0.07
     κ
    -0.07
     yr
    -0.07
    POSITIVE LOGITS
     overshadow
    0.08
    mals
    0.08
    就是说
    0.08
     вода
    0.08
    จะ
    0.07
    はい
    0.07
     recall
    0.07
    DD
    0.07
    ментов
    0.07
     glimps
    0.07
    Activations Density 0.061%

    No Known Activations