© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 44745
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    람
    -0.07
     prominently
    -0.07
     Cecil
    -0.07
    지를
    -0.07
     deportivo
    -0.07
     favoritos
    -0.07
     Curtis
    -0.07
    다면
    -0.07
     celo
    -0.07
     andar
    -0.07
    POSITIVE LOGITS
     فرم
    0.07
     */,↵
    0.07
     lia
    0.07
     pun
    0.07
     involving
    0.07
    uß
    0.07
    ský
    0.07
    wia
    0.07
     Sib
    0.07
    dsl
    0.07
    Activations Density 0.000%

    No Known Activations