© 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. 114261
    Prev
    Next
    INDEX
    Explanations

    gun

    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
     કલ
    -0.08
    -0.08
     beispielsweise
    -0.08
     odo
    -0.08
    .Highlight
    -0.08
     donnent
    -0.08
     ફોન
    -0.08
    .xy
    -0.08
    .Sequential
    -0.07
     Lisbon
    -0.07
    POSITIVE LOGITS
     rights
    0.10
     armas
    0.09
     ответственность
    0.09
     erection
    0.09
     firearms
    0.09
     Weapons
    0.09
     arsenal
    0.09
     armes
    0.09
     peace
    0.09
     legally
    0.09
    Activations Density 0.010%
    No Known Activations