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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 59787
    Prev
    Next
    INDEX
    Explanations

    checkout

    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
     tearing
    -0.10
     Sabb
    -0.08
    ец
    -0.08
     handshake
    -0.08
     triang
    -0.08
     swinging
    -0.08
     일을
    -0.08
     feud
    -0.08
    vej
    -0.07
     airplanes
    -0.07
    POSITIVE LOGITS
     tijdens
    0.10
    (税込
    0.10
     વખતે
    0.09
     этапе
    0.09
     durante
    0.09
    _checkout
    0.09
    即可
    0.08
     during
    0.08
     During
    0.08
    提交
    0.08
    Activations Density 0.032%

    No Known Activations