© 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. 52224
    Prev
    Next
    INDEX
    Explanations

    say "one"

    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
    ’at
    -0.10
    ёт
    -0.09
    um
    -0.09
     transitioning
    -0.09
    'at
    -0.08
    at
    -0.08
     getting
    -0.08
     taking
    -0.08
    назнач
    -0.08
    umidity
    -0.08
    POSITIVE LOGITS
     मे
    0.08
     survive
    0.08
     revival
    0.08
    iel
    0.08
    one
    0.07
    மை
    0.07
    മായി
    0.07
    imente
    0.07
     survives
    0.07
     jaun
    0.07
    Activations Density 0.000%

    No Known Activations