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. 67846
    Prev
    Next
    INDEX
    Explanations

    charge

    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
     платеж
    -0.08
     disco
    -0.08
    ога
    -0.08
     tên
    -0.08
    ден
    -0.07
     Cheapest
    -0.07
     landelijke
    -0.07
     Month
    -0.07
     din
    -0.07
    ними
    -0.07
    POSITIVE LOGITS
     aboard
    0.10
    اتي
    0.09
    _REGISTER
    0.08
     sepanjang
    0.08
     propositions
    0.08
     Ans
    0.08
    ying
    0.08
    ograph
    0.07
    اق
    0.07
    _CONFIRM
    0.07
    Activations Density 0.007%

    No Known Activations