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. 15-RESID-POST-AA
    6. 19340
    Prev
    Next
    INDEX
    Explanations

    The

    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
    (identity
    -0.08
    علوم
    -0.07
     Weitere
    -0.07
    ља
    -0.07
     allem
    -0.07
    zonder
    -0.07
     offrir
    -0.07
    ודעות
    -0.07
     welzijn
    -0.07
    ("↵
    -0.07
    POSITIVE LOGITS
    终于
    0.10
     footsteps
    0.09
    凉
    0.09
     trembling
    0.09
     quieter
    0.09
     sleek
    0.09
     quietly
    0.09
     crimson
    0.09
     bustling
    0.09
     buzzing
    0.09
    Activations Density 0.027%

    No Known Activations