© 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. 52088
    Prev
    Next
    INDEX
    Explanations

    O

    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
    .cd
    -0.10
    .once
    -0.09
    .fre
    -0.08
    .credentials
    -0.08
    .af
    -0.08
    Credentials
    -0.08
    .reason
    -0.08
     Credentials
    -0.08
    .hp
    -0.08
    .square
    -0.08
    POSITIVE LOGITS
    PEX
    0.16
    pex
    0.15
    &M
    0.11
    пера
    0.10
    пер
    0.10
    per
    0.10
    પર
    0.09
     perpetual
    0.09
    Per
    0.09
    ਪਰ
    0.08
    Activations Density 0.004%

    No Known Activations