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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 18446
    Prev
    Next
    INDEX
    Explanations

    logarithms

    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
     especially
    -0.09
     unforeseen
    -0.08
     insufficient
    -0.08
     unfore
    -0.08
    ,start
    -0.08
    慰
    -0.08
     홀
    -0.08
     stagn
    -0.08
    孤
    -0.07
    	where
    -0.07
    POSITIVE LOGITS
     logarith
    0.11
     лог
    0.10
     লগ
    0.09
    лог
    0.09
    _log
    0.09
     Log
    0.08
     Logs
    0.08
    log
    0.08
    Log
    0.08
     로그
    0.08
    Activations Density 0.010%

    No Known Activations