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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 30
    Prev
    Next
    INDEX
    Explanations

    mixed document types

    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
    （三
    -0.09
     à
    -0.08
    ＼
    -0.08
     jaarlijks
    -0.08
    addy
    -0.08
     criterios
    -0.08
     gezinnen
    -0.08
     Atlético
    -0.08
     પરિવ
    -0.08
     handing
    -0.08
    POSITIVE LOGITS
    Translation
    0.09
    Pagination
    0.09
    _dataset
    0.08
    Title
    0.08
    ol
    0.08
    ocado
    0.08
    Dataset
    0.08
     dataset
    0.08
     أد
    0.07
    Audio
    0.07
    Activations Density 0.353%

    No Known Activations