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. 44618
    Prev
    Next
    INDEX
    Explanations

    chemistry stoichiometry

    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
     אח
    -0.08
    ificar
    -0.08
    ônico
    -0.08
     lastig
    -0.08
    ificaciones
    -0.08
     Apo
    -0.07
     задач
    -0.07
    нят
    -0.07
     возв
    -0.07
    _tasks
    -0.07
    POSITIVE LOGITS
     supplies
    0.10
     Supplies
    0.10
     reagent
    0.09
     supplying
    0.09
     Supply
    0.09
    Supply
    0.09
     shortage
    0.09
     bath
    0.09
    .ingredients
    0.09
     hydrochlor
    0.09
    Activations Density 0.016%

    No Known Activations