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. 244
    Prev
    Next
    INDEX
    Explanations

    formatting/instructions

    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
     sigmoid
    -0.08
     reen
    -0.07
    Moreover
    -0.07
     dahil
    -0.07
    涵
    -0.07
    Submitting
    -0.07
    -inclusive
    -0.07
    Inject
    -0.07
    Signed
    -0.07
     негіз
    -0.07
    POSITIVE LOGITS
     Customize
    0.13
     customizing
    0.13
     styling
    0.12
    Customization
    0.12
     customization
    0.12
     customise
    0.12
     estilos
    0.11
    Customize
    0.11
     customize
    0.11
     Styling
    0.11
    Activations Density 0.014%

    No Known Activations