Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 102953
    Prev
    Next
    INDEX
    Explanations

    medical treatments

    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
     distint
    -0.08
     dimens
    -0.08
     سقوط
    -0.08
     hehe
    -0.08
     :)↵
    -0.08
     habilidade
    -0.08
    #undef
    -0.08
     dimensiones
    -0.08
     dimensions
    -0.08
     возникновения
    -0.08
    POSITIVE LOGITS
    治疗
    0.17
     therapies
    0.17
     medications
    0.17
     therapy
    0.15
     chemotherapy
    0.15
     치료
    0.14
     العلاج
    0.14
     терапии
    0.14
     medication
    0.14
     препарат
    0.14
    Activations Density 0.082%

    No Known Activations