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. 19192
    Prev
    Next
    INDEX
    Explanations

    summation

    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
     Similar
    -0.08
     compléter
    -0.07
    これ
    -0.07
     notamment
    -0.07
     Comple
    -0.07
    今回
    -0.07
    (data
    -0.07
     Identity
    -0.07
     particularmente
    -0.07
     completar
    -0.07
    POSITIVE LOGITS
     themselves
    0.10
     самом
    0.09
     자체
    0.09
     خپله
    0.09
     soe
    0.08
     itself
    0.08
     בתוך
    0.08
     خودش
    0.08
     people's
    0.08
    nr
    0.08
    Activations Density 0.044%

    No Known Activations