© 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. 19-RESID-POST-AA
    11. 19740
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     ultimo
    -0.09
     longstanding
    -0.08
    excluded
    -0.08
    assaq
    -0.08
     fifth
    -0.08
    lerden
    -0.08
    avali
    -0.07
    avet
    -0.07
     childs
    -0.07
     ultima
    -0.07
    POSITIVE LOGITS
    0
    0.14
    ০
    0.13
    ™
    0.12
    ०
    0.12
    D
    0.11
    ️⃣
    0.11
    ૦
    0.11
    °
    0.11
    ™↵↵
    0.11
    +:
    0.11
    Activations Density 0.016%

    No Known Activations