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. 43445
    Prev
    Next
    INDEX
    Explanations

    Acceptance and Commitment Therapy

    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
     �
    -0.09
    .hardware
    -0.09
    午
    -0.09
     Lun
    -0.09
     elektrik
    -0.09
     午
    -0.08
    .loan
    -0.08
    �
    -0.08
     Ethernet
    -0.08
    .salary
    -0.08
    POSITIVE LOGITS
     malad
    0.10
     cognitive
    0.09
     spirituality
    0.08
     underpin
    0.08
     Cognitive
    0.08
     dysfunctional
    0.08
     thereby
    0.08
     culpa
    0.08
     therapy
    0.08
     psychological
    0.08
    Activations Density 0.013%

    No Known Activations