© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 7-RESID-POST-AA
    11. 952
    Prev
    Next
    INDEX
    Explanations

    costs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     diamond
    -0.08
     przeb
    -0.08
     vreemd
    -0.08
     സ്ഥാപ
    -0.07
     കട
    -0.07
     Specialist
    -0.07
     eingef
    -0.07
     εφαρ
    -0.07
    unggu
    -0.07
     RTR
    -0.07
    POSITIVE LOGITS
     incurred
    0.08
     deeds
    0.08
    [prop
    0.07
     spor
    0.07
     unk
    0.07
    :view
    0.07
    nut
    0.07
     accrued
    0.07
    expand
    0.07
     расходов
    0.07
    Activations Density 0.027%

    No Known Activations