© 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. 7817
    Prev
    Next
    INDEX
    Explanations

    pip install packages

    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
     clan
    -0.07
     sonhos
    -0.07
    ofia
    -0.07
     dfs
    -0.07
    ultura
    -0.07
     forgive
    -0.07
    ​ស
    -0.07
     עליה
    -0.07
    -0.07
     lowercase
    -0.07
    POSITIVE LOGITS
     transit
    0.09
    တွေ
    0.09
    Transit
    0.09
     aanbevolen
    0.09
    হণ
    0.08
    গ্র
    0.08
    Werk
    0.08
    推荐
    0.08
     bran
    0.08
    Meals
    0.08
    Activations Density 0.005%
    No Known Activations