© 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. 30121
    Prev
    Next
    INDEX
    Explanations

    dependence

    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
    -0.08
     Director
    -0.08
     Joining
    -0.07
     UIView
    -0.07
     узнать
    -0.07
     NEGLIGENCE
    -0.07
     nehme
    -0.07
    	action
    -0.07
     MY
    -0.07
     DOMAIN
    -0.07
    POSITIVE LOGITS
     reliance
    0.11
     reliant
    0.10
     dependencia
    0.09
     geraakt
    0.08
    於
    0.08
     dependence
    0.08
     dependency
    0.08
    .dependencies
    0.08
     dependencies
    0.08
    dependencies
    0.08
    Activations Density 0.015%
    No Known Activations