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. 130946
    Prev
    Next
    INDEX
    Explanations

    Chinese "three"

    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
     رت
    -0.07
     DNS
    -0.07
     рез
    -0.07
     শর
    -0.07
    ప్
    -0.07
     RSI
    -0.07
     gratu
    -0.07
     administrar
    -0.07
     enr
    -0.07
     занима
    -0.07
    POSITIVE LOGITS
    亚游
    0.12
    彩神
    0.10
    里
    0.10
    里的
    0.08
     Sisters
    0.08
    水县
    0.08
    姑娘
    0.08
    龙江
    0.08
     beperk
    0.08
    052
    0.08
    Activations Density 0.001%

    No Known Activations