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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 114150
    Prev
    Next
    INDEX
    Explanations

    blue

    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
    -0.08
     aparência
    -0.08
     urlencode
    -0.07
    (Parser
    -0.07
    \Config
    -0.07
    ällen
    -0.07
     підт
    -0.07
     BILL
    -0.07
     px
    -0.07
    px
    -0.07
    POSITIVE LOGITS
    -fat
    0.08
    اليا
    0.08
    روز
    0.08
    Ах
    0.08
    この記事
    0.08
    إن
    0.08
    Understanding
    0.08
     الضوء
    0.08
    وجيه
    0.08
     فهم
    0.08
    Activations Density 0.001%
    No Known Activations