© 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. 69317
    Prev
    Next
    INDEX
    Explanations

    mathematics and functions

    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
     lockdown
    -0.10
     nurse
    -0.10
     archaeology
    -0.09
     veteran
    -0.09
     Renov
    -0.09
    _voice
    -0.09
    Elite
    -0.09
     elderly
    -0.09
    Inbound
    -0.09
    Denied
    -0.09
    POSITIVE LOGITS
     mathematic
    0.18
     Mathematical
    0.16
     mathematical
    0.16
     Algebra
    0.15
     algebra
    0.15
     математ
    0.15
     mathemat
    0.14
     Mathemat
    0.14
     mathem
    0.14
     geometric
    0.14
    Activations Density 0.060%

    No Known Activations