© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 78441
    Prev
    Next
    INDEX
    Explanations

    reverse engineering tools

    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
     childcare
    -0.11
     skirts
    -0.10
     thermostat
    -0.09
     projected
    -0.09
     शूट
    -0.09
     pillows
    -0.09
     lawn
    -0.08
     अर्ज
    -0.08
     Montessori
    -0.08
    丈
    -0.08
    POSITIVE LOGITS
     Automated
    0.08
    Annot
    0.08
    Autom
    0.08
     annot
    0.08
     jadx
    0.08
     DG
    0.08
     Annotation
    0.08
     umfang
    0.07
    Automation
    0.07
     Tools
    0.07
    Activations Density 0.003%

    No Known Activations