© 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. 19071
    Prev
    Next
    INDEX
    Explanations

    repeated

    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
     garnered
    -0.10
    prite
    -0.09
     joissa
    -0.09
     />,↵
    -0.08
    ”↵
    -0.08
    ’ed
    -0.08
    ’ve
    -0.08
    ‌కు
    -0.08
     obey
    -0.08
     وأس
    -0.08
    POSITIVE LOGITS
     use
    0.17
    _use
    0.13
    use
    0.13
    Use
    0.13
    -use
    0.13
    	use
    0.13
     usage
    0.12
     использование
    0.12
     Use
    0.12
    .use
    0.11
    Activations Density 0.005%

    No Known Activations