© 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. 23-RESID-POST-AA
    11. 50822
    Prev
    Next
    INDEX
    Explanations

    :

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     notifications
    -0.10
     height
    -0.09
    ;height
    -0.09
    height
    -0.09
     completeness
    -0.09
    	height
    -0.09
     Height
    -0.09
    Height
    -0.09
    ,height
    -0.09
     inheritance
    -0.09
    POSITIVE LOGITS
    .symmetric
    0.10
     clamp
    0.09
    50
    0.09
    40
    0.09
    ۳
    0.09
    -inline
    0.09
    3
    0.09
    ৫০
    0.08
     auto
    0.08
     주변
    0.08
    Activations Density 0.006%

    No Known Activations