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. 98658
    Prev
    Next
    INDEX
    Explanations

    Non-english text

    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
     alber
    -0.09
    -0.09
     alright
    -0.09
    오는
    -0.08
    εια
    -0.08
    োপ
    -0.08
     roster
    -0.08
     fís
    -0.08
    פיל
    -0.07
    ਤੀ
    -0.07
    POSITIVE LOGITS
    łas
    0.10
    ้ำ
    0.08
    ami
    0.08
    anej
    0.08
     เก
    0.08
    ätz
    0.08
    ashing
    0.08
    aman
    0.07
     Wieder
    0.07
    amm
    0.07
    Activations Density 0.000%

    No Known Activations