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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 68876
    Prev
    Next
    INDEX
    Explanations

    des

    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
    izante
    -0.08
    .bc
    -0.07
    issimo
    -0.07
     getter
    -0.07
    rike
    -0.07
    ethau
    -0.07
     Chun
    -0.07
     nok
    -0.07
     stomp
    -0.07
     لج
    -0.07
    POSITIVE LOGITS
    掉
    0.11
     unravel
    0.08
    afio
    0.08
     dismant
    0.07
     unw
    0.07
    flatten
    0.07
    -mentioned
    0.07
    артамент
    0.07
     fatig
    0.07
    ambigu
    0.07
    Activations Density 0.042%

    No Known Activations