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. 60446
    Prev
    Next
    INDEX
    Explanations

    ized

    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
     block
    -0.08
     Or
    -0.08
    块
    -0.07
     oleva
    -0.07
     stiffness
    -0.07
    IMITER
    -0.07
     gambler
    -0.07
    亭
    -0.07
     rou
    -0.07
     blocker
    -0.07
    POSITIVE LOGITS
     است
    0.08
     Cerca
    0.08
     keen
    0.08
     지속
    0.08
     tailored
    0.08
    chlor
    0.08
    Antwort
    0.08
     chlorine
    0.08
    ਿੱ�
    0.08
    ẹrẹ
    0.08
    Activations Density 0.001%

    No Known Activations