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. 98276
    Prev
    Next
    INDEX
    Explanations

    J

    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
     বঙ্গ
    -0.09
     svensk
    -0.08
    avnom
    -0.08
     jente
    -0.08
     Catalunya
    -0.08
     sverige
    -0.08
     Neder
    -0.08
     সম্ম
    -0.08
    еспублик
    -0.08
    িল্প
    -0.08
    POSITIVE LOGITS
    ిర
    0.10
    ir
    0.10
    irai
    0.10
    iren
    0.09
    િર
    0.09
    irar
    0.08
    िर
    0.08
    ot
    0.08
    -Air
    0.07
    ಿರ
    0.07
    Activations Density 0.000%

    No Known Activations