© 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. 63366
    Prev
    Next
    INDEX
    Explanations

    cryoprotection, genetics, Chinese

    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
     employers
    -0.08
     דיר
    -0.08
     Empresas
    -0.08
     Página
    -0.08
     Employers
    -0.07
     Household
    -0.07
     Gujarat
    -0.07
    Agr
    -0.07
     Fishing
    -0.07
     управля
    -0.07
    POSITIVE LOGITS
    िँ
    0.09
     उनी
    0.08
    ्नु
    0.08
    уы
    0.07
    /int
    0.07
    ಿಕ
    0.07
    intu
    0.07
     encycl
    0.07
    ologies
    0.07
     Erz
    0.07
    Activations Density 0.000%

    No Known Activations