© 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. 11-RESID-POST-AA
    11. 110613
    Prev
    Next
    INDEX
    Explanations

    natural

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     UML
    -0.09
     Mortgage
    -0.09
     yao
    -0.08
     Useful
    -0.08
     úteis
    -0.08
    Mortgage
    -0.08
     nedeniyle
    -0.08
     amy
    -0.08
     utiles
    -0.08
    _PERSON
    -0.07
    POSITIVE LOGITS
     alami
    0.10
    自然
    0.10
     자연
    0.09
     natural
    0.09
    natural
    0.09
     foliage
    0.09
     naturelle
    0.09
     naturel
    0.09
     flora
    0.08
     naturels
    0.08
    Activations Density 0.007%

    No Known Activations