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. 19260
    Prev
    Next
    INDEX
    Explanations

    say "or" in other languages

    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
     ABOVE
    -0.09
    :maj
    -0.08
     concerne
    -0.08
     każde
    -0.08
     lase
    -0.08
     لكل
    -0.08
     قوله
    -0.07
     adolesc
    -0.07
     அனைத்து
    -0.07
     actuator
    -0.07
    POSITIVE LOGITS
     nebo
    0.11
     или
    0.11
     或
    0.10
     また
    0.10
    하거나
    0.10
    、
    0.10
    或
    0.10
     또는
    0.09
    或者
    0.09
     �
    0.09
    Activations Density 0.443%

    No Known Activations