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. 98096
    Prev
    Next
    INDEX
    Explanations

    comma

    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
     ensuring
    -0.12
     with
    -0.11
     which
    -0.10
     verifying
    -0.10
     teniendo
    -0.10
     altering
    -0.09
     having
    -0.09
     whose
    -0.09
     illustrating
    -0.09
     helping
    -0.09
    POSITIVE LOGITS
     значит
    0.18
     онда
    0.17
     allora
    0.16
    则
    0.15
     τότε
    0.15
     significa
    0.15
     wtedy
    0.14
     entonces
    0.14
    ,则
    0.14
     alors
    0.14
    Activations Density 0.160%

    No Known Activations