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. 102702
    Prev
    Next
    INDEX
    Explanations

    Macchiato

    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
    topia
    -0.08
    Ids
    -0.07
    sexual
    -0.07
    edian
    -0.07
    esp
    -0.07
     sift
    -0.07
     preventative
    -0.07
     unprecedented
    -0.07
    竞技
    -0.07
     mantenimiento
    -0.07
    POSITIVE LOGITS
     Pong
    0.09
    .Marker
    0.08
    .Inner
    0.08
    0.07
     yayin
    0.07
     llegado
    0.07
     Seller
    0.07
     Specifies
    0.07
     Workflow
    0.07
     Variant
    0.07
    Activations Density 0.001%

    No Known Activations