© 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. 30054
    Prev
    Next
    INDEX
    Explanations

    safe

    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
    ساهم
    -0.08
     guys
    -0.08
     actu
    -0.08
     officia
    -0.08
    게
    -0.08
     incontournable
    -0.08
    indeer
    -0.07
    عيش
    -0.07
     usp
    -0.07
     ";"
    -0.07
    POSITIVE LOGITS
     гем
    0.08
     ત્યારે
    0.08
    etsa
    0.08
    大的
    0.08
     denomination
    0.08
     Pip
    0.07
    _SAFE
    0.07
     Beyond
    0.07
    Beyond
    0.07
     তখন
    0.07
    Activations Density 0.003%

    No Known Activations