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. 15-RESID-POST-AA
    6. 19277
    Prev
    Next
    INDEX
    Explanations

    breaking down tasks

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     as
    -0.09
     também
    -0.09
     also
    -0.09
     are
    -0.09
     be
    -0.08
    Correlation
    -0.08
     eveneens
    -0.08
     correlate
    -0.07
    usch
    -0.07
     '
    -0.07
    POSITIVE LOGITS
    رداری
    0.10
    或者
    0.09
     herramient
    0.09
     或
    0.09
    /...
    0.09
    илии
    0.09
    ម្ម
    0.09
     หรือ
    0.08
    рыз
    0.08
    某
    0.08
    Activations Density 0.000%

    No Known Activations