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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 113907
    Prev
    Next
    INDEX
    Explanations

    law

    np_max-act · gemini-2.0-flash

    attends to the occurrence of the end-of-sequence token "<|endoftext|>" from any token in the sequence.

    oai_attention-head · gpt-4oTriggered by @mlfinancebook
    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
     mont
    -0.08
     لتح
    -0.08
     वैश
    -0.07
     Mont
    -0.07
     NASA
    -0.07
     montage
    -0.07
     bos
    -0.07
     tun
    -0.07
     വിക
    -0.07
     Anywhere
    -0.07
    POSITIVE LOGITS
    ancial
    0.09
     spouse
    0.09
     வாழ
    0.08
     condom
    0.08
    Acknowled
    0.08
     acknowledged
    0.08
    iangle
    0.08
     thanking
    0.07
     ESP
    0.07
     acknowledgment
    0.07
    Activations Density 0.003%

    No Known Activations