© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 18440
    Prev
    Next
    INDEX
    Explanations

    avoid

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ประก
    -0.07
    .Debug
    -0.07
    .Authorization
    -0.07
    Ons
    -0.07
     INS
    -0.07
    onation
    -0.07
    on
    -0.07
    .Config
    -0.07
    .Metadata
    -0.07
     BG
    -0.07
    POSITIVE LOGITS
    Avoid
    0.43
     avoidance
    0.43
     avoid
    0.43
     Avoid
    0.42
    避免
    0.42
     vermijden
    0.42
     избег
    0.42
     evitar
    0.42
     éviter
    0.41
     avoiding
    0.41
    Activations Density 0.083%

    No Known Activations