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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 18619
    Prev
    Next
    INDEX
    Explanations

    quadratic

    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
    ચાલ
    -0.09
    specific
    -0.09
    ouvrez
    -0.08
    orage
    -0.08
    \Service
    -0.08
    _Service
    -0.08
    analyse
    -0.08
    INGS
    -0.08
    🏻
    -0.08
    TING
    -0.08
    POSITIVE LOGITS
     формы
    0.11
     forms
    0.11
     formulário
    0.10
    Forms
    0.10
     Bé
    0.10
     форму
    0.10
     form
    0.10
     μορ
    0.09
    Bezier
    0.09
    形式
    0.09
    Activations Density 0.009%

    No Known Activations