© 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. 23-RESID-POST-AA
    11. 51250
    Prev
    Next
    INDEX
    Explanations

    Spanish profanities

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     efectuar
    -0.11
     функциони
    -0.10
    องค์
    -0.10
     πραγματοποι
    -0.10
     توسعه
    -0.10
     موثر
    -0.10
     взаимодейств
    -0.09
     realizar
    -0.09
     প্রতিনিধ
    -0.09
     desempe
    -0.09
    POSITIVE LOGITS
     coño
    0.22
     mierda
    0.20
     tetas
    0.19
     chupe
    0.18
     barriga
    0.17
     novio
    0.17
     putas
    0.17
     picha
    0.16
     polla
    0.16
     perro
    0.16
    Activations Density 0.051%

    No Known Activations