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. 103171
    Prev
    Next
    INDEX
    Explanations

    Food, travel, and locations

    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
    ימוש
    -0.09
    опас
    -0.08
     નોંધ
    -0.07
     замеч
    -0.07
     fact
    -0.07
     implicitly
    -0.07
    illo
    -0.07
     Fernando
    -0.07
    	struct
    -0.07
    aket
    -0.07
    POSITIVE LOGITS
     приез
    0.13
     приех
    0.12
     Arrival
    0.11
     expatri
    0.11
     transpl
    0.11
     arrivals
    0.11
    Arrival
    0.10
     arrival
    0.10
     immigrants
    0.10
    来到
    0.10
    Activations Density 0.175%

    No Known Activations