© 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. 68231
    Prev
    Next
    INDEX
    Explanations

    if

    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
     Voyager
    -0.08
     yayi
    -0.07
     前
    -0.07
    pekto
    -0.07
    床
    -0.07
    zw
    -0.07
     NSE
    -0.07
     આવેલા
    -0.07
     �
    -0.07
    演
    -0.07
    POSITIVE LOGITS
     ترغب
    0.11
     wondering
    0.11
     muốn
    0.11
     хотите
    0.10
     möchtest
    0.10
     ingin
    0.10
     wanting
    0.10
     möchten
    0.10
    想
    0.10
     دنبال
    0.10
    Activations Density 0.028%

    No Known Activations