© 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. 23-RESID-POST-AA
    11. 51131
    Prev
    Next
    INDEX
    Explanations

    the

    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
     ڏيڻ
    -0.09
     ڏئي
    -0.09
    requires
    -0.09
     وٺ
    -0.09
     Requires
    -0.08
     requires
    -0.08
     يعتمد
    -0.08
    ично
    -0.08
     geïnteresse
    -0.08
     loves
    -0.08
    POSITIVE LOGITS
     need
    0.41
     necesidad
    0.34
     necessity
    0.33
     necessidade
    0.33
    need
    0.31
     nécessité
    0.30
    Need
    0.29
     необходимость
    0.29
     Need
    0.28
     importance
    0.27
    Activations Density 0.060%

    No Known Activations