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. 130869
    Prev
    Next
    INDEX
    Explanations

    decimal calculations

    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
    oretical
    -0.08
     popular
    -0.08
     theoretical
    -0.08
    454
    -0.07
    ord
    -0.07
    vente
    -0.07
     verific
    -0.07
    163
    -0.07
     популяр
    -0.07
     indic
    -0.07
    POSITIVE LOGITS
     Tagged
    0.09
    -ak
    0.09
     Tag
    0.09
     Suk
    0.08
     Mulungu
    0.08
     kru
    0.08
     দিব
    0.08
    -working
    0.08
    ضرار
    0.08
     prizn
    0.08
    Activations Density 0.000%

    No Known Activations