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. 15-RESID-POST-AA
    6. 19496
    Prev
    Next
    INDEX
    Explanations

    among

    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
     dynamics
    -0.08
    ipment
    -0.07
    _mutex
    -0.07
    _key
    -0.07
     Dynamics
    -0.07
    _code
    -0.07
     ndarray
    -0.07
    _ptr
    -0.07
     основе
    -0.07
     unaffected
    -0.07
    POSITIVE LOGITS
     somewhere
    0.11
     одним
    0.10
     یکی
    0.10
     إحدى
    0.10
    至少
    0.10
     לפחות
    0.10
     irgendwo
    0.10
     someplace
    0.10
     أحد
    0.09
     ضمن
    0.09
    Activations Density 0.001%

    No Known Activations