© 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. 102864
    Prev
    Next
    INDEX
    Explanations

    Also

    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
     प्रथम
    -0.09
     Δεν
    -0.09
     केवल
    -0.09
    这里只有
    -0.08
    Nein
    -0.08
     परिस्थित
    -0.08
    »↵
    -0.08
     ekki
    -0.08
    ®.
    -0.08
     അത്
    -0.08
    POSITIVE LOGITS
     include
    0.15
     добавить
    0.15
     implement
    0.15
     Additionally
    0.15
    ambahkan
    0.14
    Additionally
    0.14
     tambahan
    0.13
     əlavə
    0.13
     ayrıca
    0.13
     إضافة
    0.13
    Activations Density 0.036%

    No Known Activations