© 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. 30848
    Prev
    Next
    INDEX
    Explanations

    JSON data

    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
     vacancies
    -0.08
     insufficient
    -0.07
     brev
    -0.07
     부족
    -0.07
    اخ
    -0.07
    roh
    -0.07
    select
    -0.07
     χ
    -0.07
     chip
    -0.07
     제외
    -0.07
    POSITIVE LOGITS
     umf
    0.09
    .loads
    0.09
    <Category
    0.09
    _structure
    0.09
     geheel
    0.08
     uiteen
    0.08
     cây
    0.08
     umum
    0.08
    ::<
    0.08
     structures
    0.08
    Activations Density 0.004%

    No Known Activations