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

    Neuronpedia

    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. 15-RESID-POST-AA
    11. 16429
    Prev
    Next
    INDEX
    Explanations

    Interpreting word problems

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    տեմբերի
    -0.11
    יכת
    -0.10
     Exxon
    -0.10
     Ջ
    -0.10
     Dacă
    -0.10
     手机上的
    -0.10
    եմբերի
    -0.10
     ($("#
    -0.10
    েম্বর
    -0.10
     կամ
    -0.10
    POSITIVE LOGITS
     against
    0.07
     describes
    0.07
    against
    0.07
     Against
    0.07
    xe
    0.07
    sembling
    0.07
    semble
    0.07
     разб
    0.07
    se
    0.07
     раз
    0.07
    Activations Density 0.026%

    No Known Activations