© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 110338
    Prev
    Next
    INDEX
    Explanations

    HPA axis

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Permutation
    -0.08
     Parade
    -0.08
     parade
    -0.08
     영
    -0.08
     Apprent
    -0.07
    ições
    -0.07
     선
    -0.07
    dır
    -0.07
    Designation
    -0.07
     permutation
    -0.07
    POSITIVE LOGITS
     activity
    0.09
    _activity
    0.08
    活动
    0.08
     inactivity
    0.08
     increased
    0.08
    正常
    0.08
     activiteit
    0.08
     Aktiv
    0.08
    .enabled
    0.08
     activated
    0.08
    Activations Density 0.004%

    No Known Activations