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. 176
    Prev
    Next
    INDEX
    Explanations

    large

    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
     Fabric
    -0.08
     conceptual
    -0.08
     бөг
    -0.08
     encaps
    -0.07
     {}\
    -0.07
    Cons
    -0.07
     Reputation
    -0.07
    Consistency
    -0.07
     Ritual
    -0.07
     Ө
    -0.07
    POSITIVE LOGITS
     désormais
    0.15
     newfound
    0.14
     artık
    0.14
     πλέον
    0.14
     الجديدة
    0.14
     geworden
    0.14
    になる
    0.14
     الجديد
    0.14
     künftig
    0.13
    ening
    0.13
    Activations Density 0.288%

    No Known Activations