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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 111826
    Prev
    Next
    INDEX
    Explanations

    Intentionality/purposefulness

    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
     onmogelijk
    -0.08
     volgen
    -0.08
     Sz
    -0.08
    orale
    -0.08
     USSR
    -0.07
    GAR
    -0.07
     Shanghai
    -0.07
     gray
    -0.07
    _GR
    -0.07
    _SZ
    -0.07
    POSITIVE LOGITS
     intentional
    0.13
     purposeful
    0.12
     consciente
    0.11
     purpos
    0.10
     conscientes
    0.10
     deliberate
    0.10
    意识
    0.10
     conciencia
    0.09
     conscious
    0.09
     movimentos
    0.09
    Activations Density 0.011%

    No Known Activations