Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 103188
    Prev
    Next
    INDEX
    Explanations

    I'll just say

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    导致
    -0.08
    ходит
    -0.08
     parental
    -0.08
     Mascul
    -0.07
    表现
    -0.07
    (Enum
    -0.07
     negotiations
    -0.07
     Buffer
    -0.07
     determining
    -0.07
     negotiated
    -0.07
    POSITIVE LOGITS
     말씀
    0.12
     لكم
    0.12
     করছি
    0.11
    드립니다
    0.10
     안내
    0.10
     Vám
    0.10
     বলতে
    0.10
     хочу
    0.10
    恐縮
    0.09
    一下
    0.09
    Activations Density 0.166%

    No Known Activations