© 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. 113113
    Prev
    Next
    INDEX
    Explanations

    Cleaning and grease removal

    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
     پول
    -0.08
     inmediatamente
    -0.08
    :\\
    -0.08
     Already
    -0.08
     ids
    -0.08
    531
    -0.07
     imediatamente
    -0.07
     wavelengths
    -0.07
     immediately
    -0.07
     vocab
    -0.07
    POSITIVE LOGITS
     പ്രകട
    0.09
     combustion
    0.09
     ilma
    0.08
     chem
    0.08
     Chem
    0.08
    chem
    0.07
    radi
    0.07
    꽃
    0.07
     aerospace
    0.07
     রান
    0.07
    Activations Density 0.003%

    No Known Activations