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. 19282
    Prev
    Next
    INDEX
    Explanations

    "etcetera" 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
     the
    -0.08
    .environ
    -0.08
    иятий
    -0.08
    "For
    -0.07
     يش
    -0.07
     its
    -0.07
     મારી
    -0.07
    >The
    -0.07
    [in
    -0.07
    Attributed
    -0.07
    POSITIVE LOGITS
    など
    0.11
     وغيرها
    0.10
     എന്നീ
    0.10
    */
    ↵
    ↵
    0.10
    */,↵
    0.10
     आदि
    0.10
    等
    0.10
     */;↵
    0.10
     ஆகிய
    0.10
     */
    ↵
    ↵
    0.10
    Activations Density 0.146%

    No Known Activations