© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 102149
    Prev
    Next
    INDEX
    Explanations

    numbers

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     এসব
    -0.08
    ంలోని
    -0.08
    াৎ
    -0.08
     প্রদ
    -0.08
    াপ্ত
    -0.08
    -use
    -0.08
    երկ
    -0.08
     *)&
    -0.08
    的天天
    -0.07
    ינם
    -0.07
    POSITIVE LOGITS
     becomes
    0.11
     further
    0.11
     จะ
    0.11
     weitere
    0.10
     became
    0.10
     dals
    0.10
     يصبح
    0.10
     verdere
    0.09
    Now
    0.09
     أصبح
    0.09
    Activations Density 0.018%

    No Known Activations