© 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. 110780
    Prev
    Next
    INDEX
    Explanations

    D\&D rules

    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
    �
    -0.08
    empi
    -0.08
     diver
    -0.08
    athon
    -0.08
    365
    -0.08
    :///
    -0.07
     webdriver
    -0.07
     આમ
    -0.07
    ,test
    -0.07
     tuning
    -0.07
    POSITIVE LOGITS
     Combat
    0.10
     мона
    0.10
     बोनस
    0.09
     dégâts
    0.09
     melee
    0.08
     Damage
    0.08
     (§
    0.08
    骰
    0.08
     combats
    0.08
     Zombies
    0.08
    Activations Density 0.053%

    No Known Activations