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. 61166
    Prev
    Next
    INDEX
    Explanations

    Z

    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
    !!!!!
    -0.07
    LEAR
    -0.07
     dint
    -0.07
    منى
    -0.07
     oppure
    -0.07
     !!↵↵
    -0.07
    خور
    -0.07
     된
    -0.07
    עשה
    -0.07
    ??↵↵
    -0.07
    POSITIVE LOGITS
     
    0.09
     Ltd
    0.08
     Missouri
    0.08
    女士
    0.08
    ₂
    0.08
    akwe
    0.08
     elő
    0.07
    .glob
    0.07
     Cla
    0.07
     Viktor
    0.07
    Activations Density 0.058%

    No Known Activations