© 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. 75863
    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
    解除
    -0.07
     Braz
    -0.07
     improves
    -0.07
    出来
    -0.07
    'Etat
    -0.07
     RB
    -0.07
     は
    -0.07
    是一
    -0.07
     activ
    -0.07
    ります
    -0.07
    POSITIVE LOGITS
    Breed
    0.11
    Deal
    0.09
     cadastr
    0.08
     অক
    0.08
     முக
    0.08
     ynd
    0.08
    ofile
    0.08
    Construct
    0.08
    Neighbour
    0.08
    Weapon
    0.08
    Activations Density 0.001%

    No Known Activations