© 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. 63054
    Prev
    Next
    INDEX
    Explanations

    (@

    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
    _DOCUMENT
    -0.08
    uti
    -0.08
    581
    -0.08
     whatever
    -0.07
     ness
    -0.07
     thousand
    -0.07
    618
    -0.07
    Whatever
    -0.07
    /document
    -0.07
     attainment
    -0.07
    POSITIVE LOGITS
     vardır
    0.10
     Bürgermeister
    0.09
    많
    0.08
     Awake
    0.08
     பால
    0.08
     Args
    0.08
    0.08
    ►
    0.08
    анов
    0.08
     begleitet
    0.08
    Activations Density 0.006%
    No Known Activations