© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 102612
    Prev
    Next
    INDEX
    Explanations

    MATLAB

    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
     graphql
    -0.12
    ✨
    -0.12
    Webhook
    -0.11
    Feign
    -0.11
    �
    -0.11
    Emoji
    -0.11
     goth
    -0.11
     serde
    -0.10
     Gatsby
    -0.10
    �
    -0.10
    POSITIVE LOGITS
     MATLAB
    0.34
     Matlab
    0.29
     matlab
    0.26
     varargin
    0.23
     nargin
    0.21
    MAT
    0.21
    (varargin
    0.20
     Mathemat
    0.19
     VBA
    0.18
    argout
    0.17
    Activations Density 0.029%

    No Known Activations