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. 19566
    Prev
    Next
    INDEX
    Explanations

    because

    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
     friendliness
    -0.08
     variable
    -0.08
    UILayout
    -0.07
    ↵↵
    -0.07
    ushed
    -0.07
    -0.07
     важ
    -0.07
    iable
    -0.07
     필요한
    -0.07
    ಭ್ಯ
    -0.07
    POSITIVE LOGITS
     çünkü
    0.10
    ,因为
    0.10
    因为
    0.10
     vanwege
    0.10
     omdat
    0.09
     aufgrund
    0.09
     потому
    0.09
    _due
    0.09
     wegen
    0.09
     fordi
    0.09
    Activations Density 0.004%

    No Known Activations