© 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. 45523
    Prev
    Next
    INDEX
    Explanations

    years

    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
    _av
    -0.08
     Gourmet
    -0.08
     الأسعار
    -0.08
    visitor
    -0.08
    Has
    -0.08
    umise
    -0.07
     capables
    -0.07
     رابطه
    -0.07
    .callbacks
    -0.07
    ేవ
    -0.07
    POSITIVE LOGITS
     imprisonment
    0.12
     sentenced
    0.11
     prison
    0.11
     punishment
    0.10
     probation
    0.10
     sentencing
    0.10
    刑
    0.10
     rehabilitation
    0.10
     jail
    0.10
     convictions
    0.10
    Activations Density 0.015%

    No Known Activations