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. 19247
    Prev
    Next
    INDEX
    Explanations

    doing something again

    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
     chir
    -0.07
     فوری
    -0.07
     biggest
    -0.07
     south
    -0.07
     Exclus
    -0.07
    iguous
    -0.07
     slate
    -0.07
    तील
    -0.07
     abrupt
    -0.07
    \Extension
    -0.07
    POSITIVE LOGITS
     revisit
    0.16
     rere
    0.14
     revis
    0.13
     повтор
    0.13
     വീണ്ടും
    0.13
     Revis
    0.13
    再次
    0.12
     পুন
    0.12
     ફરી
    0.12
    重复
    0.12
    Activations Density 0.048%

    No Known Activations