© 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. 102873
    Prev
    Next
    INDEX
    Explanations

    realizing/understanding

    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
     მხოლოდ
    -0.10
     gusa
    -0.09
     élégant
    -0.09
     બધ
    -0.09
     기다
    -0.09
    끔
    -0.09
     Ако
    -0.09
     एउ
    -0.09
     élég
    -0.09
     ainult
    -0.08
    POSITIVE LOGITS
    了解到
    0.19
     понял
    0.17
    发现
    0.16
    认识
    0.16
     descubrir
    0.16
     learns
    0.16
     understand
    0.16
     realize
    0.16
     descubre
    0.16
     realizes
    0.15
    Activations Density 0.032%

    No Known Activations