© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 54689
    Prev
    Next
    INDEX
    Explanations

    exec

    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
     Riviera
    -0.08
     appreciates
    -0.08
     Award
    -0.08
    -0.07
     инду
    -0.07
     referendum
    -0.07
    .groupby
    -0.07
    .Scroll
    -0.07
    ournal
    -0.07
     жүргіз
    -0.07
    POSITIVE LOGITS
    replacement
    0.08
     replacements
    0.08
     pathname
    0.08
    Teen
    0.08
     replacement
    0.08
     loader
    0.08
     vidare
    0.07
     Replacement
    0.07
     Load
    0.07
     syscall
    0.07
    Activations Density 0.001%

    No Known Activations