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. 15-RESID-POST-AA
    6. 19103
    Prev
    Next
    INDEX
    Explanations

    code index

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ಸುಮ
    -0.08
     spo
    -0.08
     xrange
    -0.08
    풀
    -0.07
    Summ
    -0.07
    encode
    -0.07
     Summ
    -0.07
    혹
    -0.07
     hull
    -0.07
    _queue
    -0.07
    POSITIVE LOGITS
    äit
    0.10
    ’et
    0.08
    ுதிய
    0.08
    үп
    0.08
    ’clock
    0.08
    ავთ
    0.08
     reposition
    0.08
    aanut
    0.08
    äi
    0.08
    -position
    0.08
    Activations Density 0.002%

    No Known Activations