© 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. 51357
    Prev
    Next
    INDEX
    Explanations

    say "the ending -ed"

    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
     fix
    -0.09
    fix
    -0.09
     fixing
    -0.09
     trimming
    -0.08
     deactivate
    -0.08
     organising
    -0.08
     smoothing
    -0.08
    .FAIL
    -0.08
    -0.08
    compress
    -0.08
    POSITIVE LOGITS
     vaccinated
    0.27
     coated
    0.27
    (filtered
    0.27
     rotated
    0.26
     routed
    0.26
     padded
    0.26
     clustered
    0.26
     masked
    0.25
    .filtered
    0.25
     encrypted
    0.25
    Activations Density 0.322%
    No Known Activations