© 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. 11-RESID-POST-AA
    11. 71554
    Prev
    Next
    INDEX
    Explanations

    screens and mounting devices

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     who've
    -0.09
     predicts
    -0.08
     infected
    -0.08
    abalho
    -0.07
     dise
    -0.07
     greetings
    -0.07
     teaches
    -0.07
    .Messages
    -0.07
     enacted
    -0.07
     undergone
    -0.07
    POSITIVE LOGITS
    Placement
    0.12
     Placement
    0.11
     placement
    0.11
     размещ
    0.11
     размест
    0.10
     placements
    0.10
    placement
    0.10
     yerləş
    0.10
     орнал
    0.10
     placing
    0.10
    Activations Density 0.125%

    No Known Activations