© 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. 69843
    Prev
    Next
    INDEX
    Explanations

    code

    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
    ỳ
    -0.08
     cipher
    -0.08
     seasonal
    -0.08
    ERSION
    -0.08
     theatrical
    -0.08
    ❤️
    -0.08
     dubb
    -0.08
     kro
    -0.08
     tornado
    -0.08
     metaphor
    -0.08
    POSITIVE LOGITS
    letion
    0.08
     法
    0.08
    =obj
    0.08
    [obj
    0.08
    objs
    0.07
     objs
    0.07
     succeeds
    0.07
    (obj
    0.07
     അവസ
    0.07
    Objs
    0.07
    Activations Density 0.001%

    No Known Activations