© 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. 113668
    Prev
    Next
    INDEX
    Explanations

    walk

    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
     Bish
    -0.10
    TING
    -0.08
     darling
    -0.08
     Mainland
    -0.07
    Gir
    -0.07
    iation
    -0.07
     Taste
    -0.07
     yosh
    -0.07
    -rich
    -0.07
    jumlah
    -0.07
    POSITIVE LOGITS
    天下
    0.08
    踪
    0.08
    prod
    0.07
    walking
    0.07
     whisk
    0.07
    outer
    0.07
     atent
    0.07
    weise
    0.07
     vet
    0.07
     constructed
    0.07
    Activations Density 0.035%

    No Known Activations