© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 18220
    Prev
    Next
    INDEX
    Explanations

    okay

    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
    /op
    -0.10
    ?,↵
    -0.09
    /in
    -0.09
    ?),
    -0.08
    ally
    -0.08
    -of
    -0.08
     Alley
    -0.08
    /domain
    -0.08
    ssf
    -0.08
    äufe
    -0.08
    POSITIVE LOGITS
     Java
    0.08
    'T
    0.08
    ERNEL
    0.07
    	delete
    0.07
    	Get
    0.07
    ْ
    0.07
     millioner
    0.07
    �
    0.07
    	WHERE
    0.07
    ！
    0.07
    Activations Density 0.017%

    No Known Activations