© 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. 19365
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ahami
    -0.09
    ாவின்
    -0.09
    alui
    -0.09
    	this
    -0.09
     tämä
    -0.09
    后二
    -0.08
    -0.08
    gelijke
    -0.08
     הללו
    -0.08
    )this
    -0.08
    POSITIVE LOGITS
     approximately
    0.12
     وغيرها
    0.12
     περίπου
    0.11
     …
    0.11
    ...,
    0.11
     roughly
    0.11
    …
    0.11
     примерно
    0.11
     or
    0.11
    Approximately
    0.11
    Activations Density 0.019%
    No Known Activations