© 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. 23-RESID-POST-AA
    11. 5782
    Prev
    Next
    INDEX
    Explanations

    pre

    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
    imbra
    -0.10
     either
    -0.08
     ולה
    -0.08
     жидкости
    -0.07
     UNT
    -0.07
    ALK
    -0.07
     ОС
    -0.07
     ------------------------------------------------------------------------------------------------
    -0.07
     Regex
    -0.07
     applicability
    -0.07
    POSITIVE LOGITS
    mon
    0.14
    tern
    0.13
    poster
    0.13
    ord
    0.13
     arranged
    0.12
     programmed
    0.12
     mon
    0.12
    dateur
    0.12
    Mon
    0.11
    arr
    0.11
    Activations Density 0.009%

    No Known Activations