© 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. 19042
    Prev
    Next
    INDEX
    Explanations

    always (in different languages)

    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
     جديدة
    -0.10
     מחדש
    -0.10
     erneut
    -0.10
     proceeding
    -0.09
     جديد
    -0.09
     വീണ്ടും
    -0.09
     diesmal
    -0.09
    再次
    -0.09
     nuevamente
    -0.08
     THEN
    -0.08
    POSITIVE LOGITS
     항상
    0.29
     всегда
    0.28
     always
    0.28
     हमेशा
    0.27
     همیشه
    0.27
     selalu
    0.27
     altijd
    0.27
     mindig
    0.26
     ہمیشہ
    0.26
    always
    0.26
    Activations Density 0.115%

    No Known Activations