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. 12096
    Prev
    Next
    INDEX
    Explanations

    cognitive psychology

    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
     boilers
    -0.10
     trending
    -0.09
     smok
    -0.08
     devastated
    -0.08
     estate
    -0.08
     arts
    -0.08
     Steam
    -0.08
     Commonwealth
    -0.08
     laundering
    -0.08
     Yorkshire
    -0.08
    POSITIVE LOGITS
     neuroscience
    0.14
     neurosc
    0.13
     cognitive
    0.13
     cognition
    0.12
     neurons
    0.11
     neuronal
    0.11
     cerveau
    0.11
     Cognitive
    0.11
     percept
    0.11
     theories
    0.10
    Activations Density 0.023%

    No Known Activations