© 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. 113398
    Prev
    Next
    INDEX
    Explanations

    current

    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
    序
    -0.07
     Gel
    -0.07
     કરી
    -0.07
     failed
    -0.07
     Picking
    -0.07
     Buying
    -0.07
    hammer
    -0.07
     كله
    -0.07
     rõ
    -0.07
    次数
    -0.07
    POSITIVE LOGITS
     residentes
    0.10
    Residents
    0.09
     residents
    0.09
     maupun
    0.09
     supporters
    0.09
    ध
    0.09
     주민
    0.09
     colaboradores
    0.09
     subscribers
    0.09
     medewerkers
    0.09
    Activations Density 0.020%

    No Known Activations