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. 98232
    Prev
    Next
    INDEX
    Explanations

    line

    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
     οποίος
    -0.10
     bhios
    -0.09
    kanı
    -0.09
     Grøn
    -0.09
     据
    -0.09
    怎么领
    -0.09
    ाएका
    -0.09
    ณฑ
    -0.09
     伊人
    -0.09
    ħu
    -0.09
    POSITIVE LOGITS
     per
    0.10
    씩
    0.09
     tegelijk
    0.09
    Per
    0.08
    .↵↵
    0.08
     markdown
    0.08
     extensa
    0.08
     unwrap
    0.08
     формат
    0.08
     each
    0.08
    Activations Density 0.015%

    No Known Activations