© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 19161
    Prev
    Next
    INDEX
    Explanations

    环

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mezcl
    -0.09
     eclectic
    -0.08
     layered
    -0.08
    -0.08
     دقیق
    -0.08
     Union
    -0.08
     widespread
    -0.08
    ម្ប
    -0.08
    /helper
    -0.08
     mixed
    -0.07
    POSITIVE LOGITS
    —from
    0.14
    闭
    0.12
     closed
    0.12
     completo
    0.11
     komplette
    0.11
     полного
    0.11
     включая
    0.11
     geschlossen
    0.11
    closed
    0.11
     completa
    0.11
    Activations Density 0.015%
    No Known Activations