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. 109269
    Prev
    Next
    INDEX
    Explanations

    responding

    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
     hence
    -0.10
     Vold
    -0.08
     ప్రమ
    -0.08
     coroutine
    -0.08
     metro
    -0.07
    ‌స
    -0.07
     وعد
    -0.07
     torso
    -0.07
     પ્રવ
    -0.07
     household
    -0.07
    POSITIVE LOGITS
    ว่า
    0.09
    "I
    0.08
     כי
    0.08
     Affirm
    0.08
     Har
    0.08
    >({↵
    0.08
     Isi
    0.08
     clar
    0.08
     Clar
    0.08
    “I
    0.07
    Activations Density 0.018%

    No Known Activations