Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 29888
    Prev
    Next
    INDEX
    Explanations

    AppCompat

    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
    ક્ક
    -0.08
    -neutral
    -0.08
     phân
    -0.07
    ABC
    -0.07
    лич
    -0.07
     Tante
    -0.07
     footprint
    -0.07
     Eltern
    -0.07
     দ্ব
    -0.07
     жит
    -0.07
    POSITIVE LOGITS
     inaugurated
    0.08
     되고
    0.08
     Chal
    0.08
     후
    0.07
     chal
    0.07
    .Post
    0.07
     On
    0.07
     conta
    0.07
    罩
    0.07
     cổ
    0.07
    Activations Density 0.001%

    No Known Activations