© 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. 19-RESID-POST-AA
    11. 103219
    Prev
    Next
    INDEX
    Explanations

    Arrows

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ойоштор
    -0.11
     ойош
    -0.10
     सरकारले
    -0.10
     ваҡ
    -0.10
    Башҡортостан
    -0.10
     етә
    -0.10
    ություններով
    -0.10
     саҡ
    -0.10
    -0.09
     йылдың
    -0.09
    POSITIVE LOGITS
     vælge
    0.11
     pilih
    0.10
    choose
    0.10
     seleccionar
    0.10
     choose
    0.10
    _select
    0.10
     seleccion
    0.09
     선택
    0.09
     choisissez
    0.09
     chọn
    0.09
    Activations Density 0.008%
    No Known Activations