© 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. 47934
    Prev
    Next
    INDEX
    Explanations

    in

    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
     hepatic
    -0.08
     grazie
    -0.07
    onstr
    -0.07
     naquela
    -0.07
     είτε
    -0.07
    Han
    -0.07
     includes
    -0.07
    Either
    -0.07
     mêmes
    -0.07
    hyd
    -0.07
    POSITIVE LOGITS
    stieg
    0.08
     আন
    0.08
    /count
    0.08
    kere
    0.08
     surn
    0.08
     বাদ
    0.08
    /n
    0.07
    /property
    0.07
     имен
    0.07
    enth
    0.07
    Activations Density 0.003%

    No Known Activations