© 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. 11-RESID-POST-AA
    11. 203
    Prev
    Next
    INDEX
    Explanations

    gun

    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
    ieved
    -0.08
     locomotive
    -0.08
     وأضاف
    -0.08
     pok
    -0.08
     SOM
    -0.07
     driveway
    -0.07
     pobl
    -0.07
     resc
    -0.07
     cultivated
    -0.07
     coaster
    -0.07
    POSITIVE LOGITS
     lept
    0.08
    fighters
    0.08
    τι
    0.08
    workers
    0.08
    _blue
    0.08
    械
    0.08
     सामान
    0.07
     lots
    0.07
    0.07
     potent
    0.07
    Activations Density 0.008%
    No Known Activations