© 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. 95410
    Prev
    Next
    INDEX
    Explanations

    Non-Euclidean geometry

    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
    isz
    -0.08
     consign
    -0.08
     pname
    -0.07
    �
    -0.07
     confidentiality
    -0.07
     complementary
    -0.07
     gate
    -0.07
     smoke
    -0.07
     concurrency
    -0.07
    -equ
    -0.07
    POSITIVE LOGITS
     afwijk
    0.09
     abnormalities
    0.09
     anomal
    0.08
     необы
    0.08
     ungewöhn
    0.08
     anomalies
    0.08
     navegación
    0.08
     Rhode
    0.08
     неаб
    0.08
     onun
    0.08
    Activations Density 0.004%

    No Known Activations