© 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. 31019
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     paradox
    -0.08
     Europa
    -0.08
     alternativa
    -0.07
     epiderm
    -0.07
     allo
    -0.07
     escol
    -0.07
    HM
    -0.07
     contradictions
    -0.07
     Arab
    -0.07
     Milo
    -0.07
    POSITIVE LOGITS
    ，则
    0.10
    则
    0.09
    વાથી
    0.09
     כדי
    0.09
    ，将
    0.08
    的时候
    0.08
    后的
    0.08
    เพื่อ
    0.08
     দিলে
    0.08
    进去
    0.08
    Activations Density 0.079%

    No Known Activations