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. 77225
    Prev
    Next
    INDEX
    Explanations

    positional encoding/formulas

    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
     marketplaces
    -0.08
    主
    -0.08
     marketplace
    -0.08
     tu
    -0.07
     вед
    -0.07
    جه
    -0.07
     التجارية
    -0.07
     voorbereiding
    -0.07
     VMware
    -0.07
     Basket
    -0.07
    POSITIVE LOGITS
    Encoding
    0.09
    Embedding
    0.09
    expo
    0.09
     débar
    0.08
    Encode
    0.08
    encode
    0.08
     encode
    0.08
     eröff
    0.08
     Encoding
    0.08
     physic
    0.08
    Activations Density 0.001%

    No Known Activations