© 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. 19-RESID-POST-AA
    11. 102665
    Prev
    Next
    INDEX
    Explanations

    hour

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pedra
    -0.08
    硕
    -0.08
     ladr
    -0.08
    -0.08
     pede
    -0.07
    mızı
    -0.07
     fueled
    -0.07
     pomme
    -0.07
     pierre
    -0.07
    =model
    -0.07
    POSITIVE LOGITS
     hour
    0.14
     अवधि
    0.11
     angle
    0.11
    hour
    0.11
    Hour
    0.11
     שעה
    0.11
    -hour
    0.11
     hours
    0.11
    _hour
    0.10
     Hour
    0.10
    Activations Density 0.001%
    No Known Activations