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. 98511
    Prev
    Next
    INDEX
    Explanations

    .

    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
     zap
    -0.08
    Sm
    -0.08
    sm
    -0.08
    Wt
    -0.08
    ંત
    -0.07
    .sm
    -0.07
    'Europe
    -0.07
     sm
    -0.07
     lif
    -0.07
     lebens
    -0.07
    POSITIVE LOGITS
    ān
    0.09
    ree
    0.08
    ox
    0.07
    ā
    0.07
    tọ
    0.07
    ată
    0.07
     내
    0.07
    či
    0.07
    /common
    0.07
     ye
    0.07
    Activations Density 0.009%

    No Known Activations