© 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. 110738
    Prev
    Next
    INDEX
    Explanations

    packaging

    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
     కలిసి
    -0.08
     locomotive
    -0.08
    十
    -0.08
    	speed
    -0.07
     antre
    -0.07
     geek
    -0.07
     fichiers
    -0.07
     montage
    -0.07
     empreendedor
    -0.07
     количе
    -0.07
    POSITIVE LOGITS
     funnels
    0.09
     redesign
    0.08
     Funnel
    0.08
    方案
    0.08
     Funnels
    0.08
    0.08
     Options
    0.08
    sche
    0.08
     funnel
    0.07
    .large
    0.07
    Activations Density 0.008%
    No Known Activations