© 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. 7-RESID-POST-AA
    11. 1481
    Prev
    Next
    INDEX
    Explanations

    quartz

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     conventions
    -0.09
     celle
    -0.08
     convention
    -0.08
     gauche
    -0.08
     izquierda
    -0.08
     الامر
    -0.08
     esconder
    -0.08
     hiding
    -0.08
     condensed
    -0.08
     laissé
    -0.07
    POSITIVE LOGITS
     Xu
    0.08
    挣
    0.08
    mei
    0.08
    onesa
    0.08
     pux
    0.08
    0.07
     prosper
    0.07
    自治
    0.07
     inexist
    0.07
     ಸರ
    0.07
    Activations Density 0.002%
    No Known Activations