© 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. 114089
    Prev
    Next
    INDEX
    Explanations

    calendar

    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
     strengthening
    -0.08
    oret
    -0.08
     strengthens
    -0.08
     fortalecer
    -0.08
     ジ
    -0.08
    nst
    -0.08
     strengthened
    -0.08
     JOB
    -0.08
     Jurassic
    -0.08
     DIRE
    -0.07
    POSITIVE LOGITS
     gä
    0.07
     поправ
    0.07
    HE
    0.07
     omi
    0.07
    £
    0.07
     debug
    0.07
    ਾਨਕ
    0.07
     Annie
    0.07
     commune
    0.07
     sulis
    0.07
    Activations Density 0.001%

    No Known Activations