© 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. 19-RESID-POST-AA
    11. 18284
    Prev
    Next
    INDEX
    Explanations

    Oracle

    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
     Malmö
    -0.11
     Finnish
    -0.10
     Mathf
    -0.09
     Senegal
    -0.09
     Svenska
    -0.09
     Swedish
    -0.09
     Göteborg
    -0.09
     crochet
    -0.08
     wagt
    -0.08
     Baltic
    -0.08
    POSITIVE LOGITS
     Oracle
    0.24
    Oracle
    0.21
     oracle
    0.20
    .oracle
    0.20
    oracle
    0.18
     OCI
    0.17
    Ora
    0.16
    ORA
    0.15
    _OR
    0.14
    .OR
    0.14
    Activations Density 0.008%

    No Known Activations