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. 23-RESID-POST-AA
    6. 130920
    Prev
    Next
    INDEX
    Explanations

    ("

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kad
    -0.09
     ik
    -0.07
     Kub
    -0.07
     Paul's
    -0.07
     IC
    -0.07
     قراءة
    -0.07
    Gc
    -0.07
    _G
    -0.07
    Kad
    -0.06
    _SM
    -0.06
    POSITIVE LOGITS
    $LANG
    0.09
     noveller
    0.09
     অতিথ
    0.09
    អ្នក
    0.09
     biex
    0.08
     PICKS
    0.08
    шон
    0.08
    ახლ
    0.08
     shafts
    0.08
     camere
    0.08
    Activations Density 0.000%

    No Known Activations