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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 113593
    Prev
    Next
    INDEX
    Explanations

    Card games

    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
     micro
    -0.07
     Rust
    -0.07
     displacement
    -0.07
     Pod
    -0.07
     Idaho
    -0.07
     landscaping
    -0.07
     surpass
    -0.07
     encaps
    -0.07
     perce
    -0.07
    arris
    -0.07
    POSITIVE LOGITS
    Matched
    0.10
    Matching
    0.09
     verkocht
    0.09
    matched
    0.09
    ��
    0.09
     exhausted
    0.09
     vendidos
    0.09
     dragged
    0.09
    Attempt
    0.09
     exhausting
    0.08
    Activations Density 0.004%

    No Known Activations