© 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. 11-RESID-POST-AA
    11. 111535
    Prev
    Next
    INDEX
    Explanations

    ability, skill

    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
    eness
    -0.08
    �
    -0.08
    ाए
    -0.08
     cà
    -0.08
     संस्थ
    -0.08
     Qur
    -0.08
    _measure
    -0.08
     borderline
    -0.07
     informat
    -0.07
     измер
    -0.07
    POSITIVE LOGITS
     cooldown
    0.11
    Cooldown
    0.10
     talent
    0.08
    cool
    0.08
     grenade
    0.08
     inhibitors
    0.08
     weapon
    0.08
     кул
    0.07
    matig
    0.07
     burning
    0.07
    Activations Density 0.004%

    No Known Activations