© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 69728
    Prev
    Next
    INDEX
    Explanations

    Extracted text segments

    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
     congratulations
    -0.09
     perfecte
    -0.08
    机器
    -0.08
    _statistics
    -0.08
     peso
    -0.08
     rendimiento
    -0.07
    ано
    -0.07
     কিন
    -0.07
    anding
    -0.07
    _encoded
    -0.07
    POSITIVE LOGITS
     walkers
    0.08
     behaving
    0.08
     behaves
    0.08
     fugit
    0.08
    坡
    0.07
    Parms
    0.07
    elike
    0.07
     sere
    0.07
    .il
    0.07
    Modifiers
    0.07
    Activations Density 0.000%

    No Known Activations