© 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. 113384
    Prev
    Next
    INDEX
    Explanations

    Sunday

    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
     সম্ম
    -0.08
     fac
    -0.07
    deal
    -0.07
    cant
    -0.07
    'ét
    -0.07
    formations
    -0.07
     Brandenburg
    -0.07
    ε
    -0.07
    Vertices
    -0.07
     usual
    -0.06
    POSITIVE LOGITS
     horseback
    0.09
     Hardy
    0.08
     preacher
    0.08
     Ravi
    0.08
    -most
    0.08
     Sundays
    0.08
     kitten
    0.08
     domingo
    0.08
    ître
    0.08
     Woche
    0.08
    Activations Density 0.008%

    No Known Activations