© 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. 102449
    Prev
    Next
    INDEX
    Explanations

    in

    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
    ικού
    -0.11
     kumbe
    -0.10
     fahrenden
    -0.10
     hefði
    -0.10
    ագույն
    -0.10
     naswona
    -0.10
     txiv
    -0.10
     տուն
    -0.10
     knull
    -0.10
     Xikwembu
    -0.10
    POSITIVE LOGITS
     diferents
    0.12
    รายละเอียด
    0.11
    циями
    0.11
     വിശദ
    0.10
     подроб
    0.10
     التفاصيل
    0.10
     વિગતો
    0.10
     diferentes
    0.10
     detay
    0.09
     المختلفة
    0.09
    Activations Density 0.000%

    No Known Activations