© 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. 65384
    Prev
    Next
    INDEX
    Explanations

    example

    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
     paved
    -0.08
    bundet
    -0.08
    pler
    -0.07
     href
    -0.07
     grep
    -0.07
    plings
    -0.07
    atea
    -0.07
     potentially
    -0.07
    ulog
    -0.07
     gateways
    -0.07
    POSITIVE LOGITS
     Illustration
    0.13
     Illustr
    0.13
     illustrate
    0.13
     hipot
    0.12
    illustr
    0.12
    Illustr
    0.12
     illustrative
    0.12
     illustrates
    0.12
     illustr
    0.12
     illustration
    0.11
    Activations Density 0.028%

    No Known Activations