Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 65483
    Prev
    Next
    INDEX
    Explanations

    software interfaces

    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
     burn
    -0.08
     haya
    -0.07
    Has
    -0.07
    Aws
    -0.07
    هود
    -0.07
     শুক
    -0.07
     étr
    -0.07
     hayan
    -0.07
    ?.↵
    -0.07
     evaporation
    -0.07
    POSITIVE LOGITS
    打开
    0.14
     openen
    0.12
     initiating
    0.11
     öffnen
    0.11
    打不开
    0.11
    开启
    0.11
    启动
    0.11
     Initi
    0.11
     iniciar
    0.11
     membuka
    0.10
    Activations Density 0.036%

    No Known Activations