Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RESID-POST-AA
    6. 52987
    Prev
    Next
    INDEX
    Explanations

    zero

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ודית
    -0.08
     sawijining
    -0.08
     kruis
    -0.08
    iast
    -0.08
    chaus
    -0.08
    astes
    -0.08
    داخل
    -0.08
    essions
    -0.08
     generosity
    -0.08
    281
    -0.07
    POSITIVE LOGITS
    رك
    0.09
    .Java
    0.07
    稱
    0.07
    öm
    0.07
    .count
    0.07
     全
    0.07
     pure
    0.07
    (count
    0.07
     Leroy
    0.07
    xff
    0.07
    Activations Density 0.018%

    No Known Activations