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. 123
    Prev
    Next
    INDEX
    Explanations

    ready

    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
     בתחום
    -0.08
    hart
    -0.07
     peaked
    -0.07
     hovering
    -0.07
     overlapping
    -0.07
     zkušen
    -0.07
     crashed
    -0.07
    izona
    -0.07
     întâ
    -0.07
     nhập
    -0.07
    POSITIVE LOGITS
    准备
    0.11
     तैयार
    0.11
     آماده
    0.11
     તૈયાર
    0.11
     hurried
    0.10
    Ready
    0.10
     pripr
    0.10
    _ready
    0.10
     propel
    0.10
     തയ്യാറ
    0.10
    Activations Density 0.050%

    No Known Activations