© 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. 70444
    Prev
    Next
    INDEX
    Explanations

    Chart

    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
    те
    -0.07
    friend
    -0.07
     awkward
    -0.07
    (Cs
    -0.07
    �
    -0.07
    никами
    -0.07
    поч
    -0.07
     Lucia
    -0.07
    >';
↵
    -0.07
    ved
    -0.07
    POSITIVE LOGITS
     cognitive
    0.07
    Item
    0.07
    ềm
    0.07
    endif
    0.07
     הי
    0.07
    188
    0.07
    manda
    0.07
     [[[
    0.07
     endocrine
    0.07
    osh
    0.07
    Activations Density 0.191%

    No Known Activations