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

    Neuronpedia

    APICircuit 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. 88256
    Prev
    Next
    INDEX
    Explanations

    isher/finishing

    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
     agree
    -0.08
    Gs
    -0.07
    plet
    -0.07
     Guys
    -0.07
    etas
    -0.07
     expanding
    -0.07
    javax
    -0.07
     urllib
    -0.07
     goodness
    -0.06
    uture
    -0.06
    POSITIVE LOGITS
    551
    0.09
     علام
    0.08
    миз
    0.08
     Р
    0.08
     वक्त
    0.08
     gärna
    0.08
     بیان
    0.08
     gestures
    0.08
     öfter
    0.08
    }`↵
    0.08
    Activations Density 0.002%

    No Known Activations