© 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. 110747
    Prev
    Next
    INDEX
    Explanations

    ,

    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
    	describe
    -0.09
    Unset
    -0.08
    taxonomy
    -0.08
     discutir
    -0.08
    mere
    -0.08
     আলোচনা
    -0.08
    committee
    -0.08
    institution
    -0.08
     geple
    -0.08
     imprint
    -0.08
    POSITIVE LOGITS
    金币
    0.10
     gameplay
    0.10
     штраф
    0.10
    奖励
    0.10
     rewards
    0.09
    _reward
    0.09
     autoplay
    0.09
     Rewards
    0.09
    _rewards
    0.09
    stacle
    0.09
    Activations Density 0.064%

    No Known Activations