© 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. 68221
    Prev
    Next
    INDEX
    Explanations

    Code/formatted text

    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
     tapi
    -0.08
     Paw
    -0.07
     KDE
    -0.07
     biod
    -0.07
     Zh
    -0.07
    -Germain
    -0.07
    Client
    -0.07
     schö
    -0.07
     biodegradable
    -0.07
    VS
    -0.07
    POSITIVE LOGITS
    -ক
    0.08
     Compar
    0.08
    @Run
    0.08
     compar
    0.08
     Comparison
    0.07
     విడ
    0.07
    计
    0.07
     auta
    0.07
    uited
    0.07
    ल्या
    0.07
    Activations Density 0.001%

    No Known Activations