© 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. 68657
    Prev
    Next
    INDEX
    Explanations

    animal speed

    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
     planned
    -0.09
     liberal
    -0.08
     gown
    -0.08
    予定
    -0.08
    الو
    -0.08
     flavors
    -0.07
     бөл
    -0.07
     alphabetical
    -0.07
     receiving
    -0.07
     trending
    -0.07
    POSITIVE LOGITS
     prowess
    0.10
     قدرة
    0.09
     maksimum
    0.09
     capacités
    0.09
     feats
    0.09
     abilities
    0.09
    能力
    0.09
     Maximum
    0.09
     kemampuan
    0.09
    猎
    0.09
    Activations Density 0.009%

    No Known Activations