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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 103066
    Prev
    Next
    INDEX
    Explanations

    if

    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
     Barr
    -0.08
     تقييم
    -0.08
     begleiten
    -0.07
     当
    -0.07
    үүр
    -0.07
     أو
    -0.07
     yaklaşık
    -0.07
    طلاب
    -0.07
     恒
    -0.07
    иков
    -0.07
    POSITIVE LOGITS
    -changing
    0.08
    -responsive
    0.08
     hoje
    0.08
     freshness
    0.08
    -change
    0.08
    chang
    0.08
     show's
    0.08
    사진
    0.08
    Donald's
    0.08
    Today
    0.08
    Activations Density 0.000%

    No Known Activations