© 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. 18482
    Prev
    Next
    INDEX
    Explanations

    phr

    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
    	to
    -0.10
     routinely
    -0.09
    tenir
    -0.09
    /{{$
    -0.09
    nullptr
    -0.09
     varmasti
    -0.09
     автоматически
    -0.08
     inevitably
    -0.08
     sicuramente
    -0.08
    	for
    -0.08
    POSITIVE LOGITS
    étation
    0.11
    ение
    0.11
    actice
    0.10
    asing
    0.10
    ased
    0.10
    าณ
    0.10
     wording
    0.10
    ation
    0.10
    ism
    0.09
    ization
    0.09
    Activations Density 0.004%

    No Known Activations