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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 55963
    Prev
    Next
    INDEX
    Explanations

    active listening

    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
     fabricantes
    -0.08
     устройство
    -0.08
     покупателей
    -0.08
     автомобили
    -0.08
    _JOB
    -0.07
     fabricante
    -0.07
     vigilancia
    -0.07
                                                                    
    -0.07
    监
    -0.07
     шокол
    -0.07
    POSITIVE LOGITS
     apology
    0.10
    gist
    0.09
     elic
    0.09
    ,说
    0.09
     empath
    0.09
     mental
    0.09
     empathy
    0.09
     condol
    0.09
     verbal
    0.08
    一句
    0.08
    Activations Density 0.024%

    No Known Activations