© 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. 29116
    Prev
    Next
    INDEX
    Explanations

    Plate tectonics/subduction

    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
     gestern
    -0.10
     tomorrow
    -0.09
     завтра
    -0.08
     allegedly
    -0.08
     Monday
    -0.08
     gisteren
    -0.08
    LOL
    -0.08
     सुबह
    -0.07
     вчера
    -0.07
     прошл
    -0.07
    POSITIVE LOGITS
     exploitation
    0.09
    挡
    0.08
     mener
    0.08
     sfr
    0.08
     tritur
    0.08
     fruitful
    0.08
     bile
    0.08
     fierc
    0.07
     naissance
    0.07
     explotación
    0.07
    Activations Density 0.004%

    No Known Activations