© 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. 1408
    Prev
    Next
    INDEX
    Explanations

    not

    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
    POP
    -0.08
    �
    -0.08
    تن
    -0.07
    zhi
    -0.07
    毅
    -0.07
     Holt
    -0.07
    ेख
    -0.07
    虐
    -0.07
    纸
    -0.07
    址
    -0.07
    POSITIVE LOGITS
     উদ্দেশ
    0.10
     Zweck
    0.10
     목적
    0.09
    Purpose
    0.09
     Purpose
    0.09
     warranted
    0.09
     предназнач
    0.09
    用途
    0.09
     purpose
    0.09
     deseas
    0.08
    Activations Density 0.095%

    No Known Activations