© 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. 23-RESID-POST-AA
    11. 50032
    Prev
    Next
    INDEX
    Explanations

    Google API and python

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    USD
    -0.08
     school's
    -0.08
    870
    -0.08
     Konto
    -0.08
     tiền
    -0.08
     تل
    -0.08
     company's
    -0.08
    895
    -0.07
     insurer
    -0.07
     Embedded
    -0.07
    POSITIVE LOGITS
    .discovery
    0.11
    ap
    0.10
     discovery
    0.09
     discoveries
    0.09
    transport
    0.08
    -resource
    0.08
    spaces
    0.08
    -auth
    0.08
     Dunn
    0.08
    size
    0.08
    Activations Density 0.001%

    No Known Activations