© 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. 52180
    Prev
    Next
    INDEX
    Explanations

    the

    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
     PDF
    -0.09
     adjustable
    -0.09
     textured
    -0.09
     PWM
    -0.09
     scaler
    -0.09
     realtime
    -0.09
     classy
    -0.09
     sticker
    -0.09
     coefficient
    -0.09
     слегка
    -0.09
    POSITIVE LOGITS
     repentance
    0.20
     conquest
    0.19
     betrayal
    0.18
     imprisonment
    0.18
    Battle
    0.18
     Battle
    0.18
     destruction
    0.17
     massacre
    0.17
     resurrection
    0.17
     defeat
    0.17
    Activations Density 0.070%

    No Known Activations