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. 130883
    Prev
    Next
    INDEX
    Explanations

    Ant

    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
    irat
    -0.09
     subpo
    -0.08
    clud
    -0.08
     Hawaii
    -0.08
    okeo
    -0.08
    undef
    -0.08
    erings
    -0.08
    erb
    -0.08
     commute
    -0.08
     undef
    -0.08
    POSITIVE LOGITS
    ,V
    0.09
    خط
    0.09
    /V
    0.09
    "G
    0.09
    -V
    0.08
    .V
    0.08
     labeled
    0.08
     V
    0.07
     onc
    0.07
    agon
    0.07
    Activations Density 0.000%

    No Known Activations