© 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. 23-RESID-POST-AA
    11. 52021
    Prev
    Next
    INDEX
    Explanations

    height

    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
    Negative Logits
     x
    -0.16
    -x
    -0.16
     horizontally
    -0.16
     widths
    -0.15
     horizontal
    -0.15
    ,x
    -0.15
    .longitude
    -0.15
    	x
    -0.15
     width
    -0.15
     Width
    -0.15
    POSITIVE LOGITS
     height
    0.20
    Height
    0.19
    _height
    0.19
    .height
    0.19
    _HEIGHT
    0.18
    	height
    0.18
    (height
    0.18
    height
    0.18
     Height
    0.18
     vertically
    0.17
    Activations Density 0.044%

    No Known Activations