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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 44556
    Prev
    Next
    INDEX
    Explanations

    worship

    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
     Inser
    -0.08
     잡
    -0.08
    trat
    -0.07
     Elimin
    -0.07
     Leasing
    -0.07
    $o
    -0.07
    算
    -0.07
    $s
    -0.07
    -0.07
     obi
    -0.07
    POSITIVE LOGITS
     worship
    0.09
     hur
    0.08
     मुक्त
    0.08
    �
    0.08
     spectroscopy
    0.08
     distra
    0.08
     distract
    0.07
     activities
    0.07
     cand
    0.07
    �
    0.07
    Activations Density 0.005%
    No Known Activations