© 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. 18758
    Prev
    Next
    INDEX
    Explanations

    nutrients

    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
     annot
    -0.09
     commemor
    -0.08
     school's
    -0.08
     divulg
    -0.08
     annotate
    -0.08
     зориул
    -0.08
     memorandum
    -0.08
     ಕುರಿತು
    -0.08
    -auth
    -0.08
     commemorate
    -0.07
    POSITIVE LOGITS
     content
    0.12
     contenido
    0.12
     nutrients
    0.12
     buildup
    0.12
     الموجودة
    0.11
     additives
    0.11
     вещества
    0.11
     minerals
    0.11
     receptors
    0.11
     stoffen
    0.11
    Activations Density 0.095%

    No Known Activations