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. 58945
    Prev
    Next
    INDEX
    Explanations

    said

    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
     दूसरा
    -0.07
    mage
    -0.07
     അന്വേഷണം
    -0.07
     yox
    -0.07
    vention
    -0.07
     estre
    -0.07
     którego
    -0.07
     Escape
    -0.07
    hag
    -0.07
     aconse
    -0.07
    POSITIVE LOGITS
     theoretically
    0.14
     aspirations
    0.13
     intentions
    0.12
     theoretical
    0.12
     ambitions
    0.12
     intending
    0.10
     intention
    0.10
     ambitie
    0.10
     ambition
    0.10
     kuitenkin
    0.10
    Activations Density 0.103%

    No Known Activations