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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 48894
    Prev
    Next
    INDEX
    Explanations

    держ

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    दान
    -0.09
    lying
    -0.09
    сор
    -0.09
    ство
    -0.08
    ্ঠ
    -0.08
    чез
    -0.08
    ficos
    -0.08
    ธ์
    -0.08
    ствуют
    -0.08
    ficamente
    -0.08
    POSITIVE LOGITS
    ателем
    0.15
    атели
    0.14
    ался
    0.13
    ать
    0.13
    ателями
    0.12
    ателей
    0.12
    ались
    0.12
    ателям
    0.12
    итесь
    0.12
    аться
    0.11
    Activations Density 0.002%

    No Known Activations