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. 98138
    Prev
    Next
    INDEX
    Explanations

    Mixed code and Russian

    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
     Whole
    -0.08
     ware
    -0.08
    ைய
    -0.08
     sweet
    -0.07
    .decode
    -0.07
    che
    -0.07
     cou
    -0.07
    .parse
    -0.07
    whole
    -0.07
     Curious
    -0.07
    POSITIVE LOGITS
    भारत
    0.08
    ्थ
    0.08
    ствует
    0.08
    Stephen
    0.08
    νού
    0.08
     кот
    0.08
    бав
    0.08
     accommodated
    0.08
     abge
    0.07
    _VAR
    0.07
    Activations Density 0.000%

    No Known Activations