© 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. 11-RESID-POST-AA
    11. 68755
    Prev
    Next
    INDEX
    Explanations

    ement

    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
     angenehm
    -0.09
    ивет
    -0.08
     battered
    -0.08
     persen
    -0.08
     rente
    -0.08
    pea
    -0.08
    pep
    -0.08
    ビュー
    -0.08
     электрон
    -0.08
     sprouts
    -0.08
    POSITIVE LOGITS
     crimes
    0.08
    266
    0.07
     Bryan
    0.07
     Antoni
    0.07
    .cpp
    0.07
     installation
    0.07
    记
    0.07
     खेल
    0.07
     Ireland
    0.07
     کھیل
    0.07
    Activations Density 0.002%

    No Known Activations