© 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. 47837
    Prev
    Next
    INDEX
    Explanations

    Sandwiches

    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
     chocolates
    -0.08
    িউজ
    -0.08
    -0.08
    _Array
    -0.08
    (stack
    -0.07
    _Type
    -0.07
    Shortest
    -0.07
    二维
    -0.07
    iori
    -0.07
    czne
    -0.07
    POSITIVE LOGITS
     exaggerated
    0.09
     Prez
    0.08
    �
    0.08
     amplification
    0.08
     Warm
    0.08
     Some
    0.08
     quo
    0.08
     бренд
    0.08
     Empire
    0.08
    0.07
    Activations Density 0.008%
    No Known Activations