© 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. 52095
    Prev
    Next
    INDEX
    Explanations

    classical texts

    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
     gastos
    -0.08
    _hook
    -0.07
     Barry
    -0.07
    �
    -0.07
    .capacity
    -0.07
     gastronom
    -0.07
    177
    -0.07
    اؤن
    -0.07
     FSC
    -0.07
     cht
    -0.07
    POSITIVE LOGITS
    િજ
    0.09
    ിജ
    0.09
    High
    0.08
     IDs
    0.08
    .High
    0.08
    িদ
    0.08
    (high
    0.08
    ične
    0.08
    rut
    0.08
    rvats
    0.08
    Activations Density 0.000%

    No Known Activations