© 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. 102795
    Prev
    Next
    INDEX
    Explanations

    这里

    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
     یہاں
    -0.13
     Here
    -0.13
     здесь
    -0.13
    Here
    -0.13
     هنا
    -0.13
     כאן
    -0.13
     այստեղ
    -0.13
    ここ
    -0.13
    Aquí
    -0.12
     tutaj
    -0.12
    POSITIVE LOGITS
     also
    0.14
    ’s
    0.11
     we
    0.11
    's
    0.11
     you
    0.11
     தான்
    0.11
     is
    0.10
     también
    0.10
    bei
    0.10
     важно
    0.10
    Activations Density 0.008%

    No Known Activations