© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 20185
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     quod
    -0.08
    -0.08
    ácia
    -0.07
     komplette
    -0.07
     нив
    -0.07
    �
    -0.07
     completos
    -0.07
    quarta
    -0.07
     indépend
    -0.07
     reale
    -0.07
    POSITIVE LOGITS
     limited
    0.15
    Limited
    0.14
    limited
    0.14
     Limited
    0.14
     beperkte
    0.14
     beperkt
    0.13
     limité
    0.13
     pochi
    0.12
     wenigen
    0.12
     രണ്ട്
    0.12
    Activations Density 0.062%
    No Known Activations