© 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. 65
    Prev
    Next
    INDEX
    Explanations

    app

    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
     lookout
    -0.08
     акс
    -0.08
    137
    -0.08
     sky
    -0.08
     uppt
    -0.08
     uche
    -0.08
     beard
    -0.07
     proposing
    -0.07
    689
    -0.07
     ajorn
    -0.07
    POSITIVE LOGITS
    sample
    0.08
    metrics
    0.08
    ampled
    0.08
    ave
    0.08
     subjected
    0.08
    lld
    0.08
     undergoing
    0.08
    対象
    0.08
     unfolding
    0.08
    Analyzer
    0.07
    Activations Density 0.010%

    No Known Activations