© 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. 44287
    Prev
    Next
    INDEX
    Explanations

    prompt/question

    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
    �
    -0.08
    කා
    -0.07
    ଶ
    -0.07
     recoil
    -0.07
    م
    -0.07
    ନ
    -0.07
    šel
    -0.07
     imaging
    -0.07
    ವಾಗಿ
    -0.07
     OC
    -0.07
    POSITIVE LOGITS
     préciser
    0.08
    igue
    0.08
     beforehand
    0.08
     уточ
    0.08
     dores
    0.08
    _into
    0.07
     précédente
    0.07
     toucher
    0.07
     Kane
    0.07
     piernas
    0.07
    Activations Density 0.014%

    No Known Activations