© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 48112
    Prev
    Next
    INDEX
    Explanations

    recognition

    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
     отоп
    -0.10
     bedroom
    -0.09
    _storage
    -0.08
     ನೀ
    -0.08
     potable
    -0.08
     shale
    -0.08
     plomberie
    -0.08
     groundwater
    -0.08
     кип
    -0.08
     kettle
    -0.08
    POSITIVE LOGITS
     recognition
    0.21
     receptors
    0.20
     Recognition
    0.20
    Recognition
    0.20
     recognizing
    0.19
     recognize
    0.19
     ligand
    0.18
     recognizes
    0.18
     receptor
    0.18
     lig
    0.17
    Activations Density 0.018%

    No Known Activations