© 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. 129475
    Prev
    Next
    INDEX
    Explanations

    multiplication

    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
    処
    -0.09
    働
    -0.08
    Crawler
    -0.08
    Placeholder
    -0.08
    merk
    -0.07
    Upd
    -0.07
     keinem
    -0.07
     kosong
    -0.07
    Tokenizer
    -0.07
     ગયો
    -0.07
    POSITIVE LOGITS
     sarà
    0.08
     midnight
    0.07
     Será
    0.07
     durable
    0.07
     serà
    0.07
    react
    0.07
    scope
    0.07
     máquina
    0.07
     rush
    0.07
    无线
    0.07
    Activations Density 0.001%

    No Known Activations