© 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. 113298
    Prev
    Next
    INDEX
    Explanations

    Usually

    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
     затем
    -0.08
     vervolgens
    -0.08
     dalších
    -0.08
    ignored
    -0.08
     слой
    -0.08
     asupra
    -0.08
     darunter
    -0.07
     Explained
    -0.07
     tovább
    -0.07
     Helic
    -0.07
    POSITIVE LOGITS
     billi
    0.08
     convention
    0.08
    Michael
    0.08
     contest
    0.08
    锅
    0.07
     typical
    0.07
     nowadays
    0.07
     characteristic
    0.07
     problems
    0.07
    套路
    0.07
    Activations Density 0.040%

    No Known Activations