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. 112983
    Prev
    Next
    INDEX
    Explanations

    Money

    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
     hare
    -0.09
     closely
    -0.09
    측
    -0.08
    _using
    -0.08
     meydana
    -0.07
    etus
    -0.07
    -0.07
     మ
    -0.07
     môi
    -0.07
     লক্ষ
    -0.07
    POSITIVE LOGITS
    Dam
    0.08
     bills
    0.08
     circulación
    0.08
     filed
    0.08
     પુ
    0.08
     donations
    0.08
     خالد
    0.08
    Pile
    0.08
     donated
    0.08
    verified
    0.08
    Activations Density 0.006%

    No Known Activations