© 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. 11-RESID-POST-AA
    11. 26220
    Prev
    Next
    INDEX
    Explanations

    dispute resolution

    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
     qəbul
    -0.07
    影片
    -0.07
    jective
    -0.07
    grammar
    -0.07
     ਦਰ
    -0.07
    šč
    -0.06
     inhibitor
    -0.06
     afirmar
    -0.06
     Ded
    -0.06
    ying
    -0.06
    POSITIVE LOGITS
     remedies
    0.10
     preferable
    0.10
    Retries
    0.09
     попроб
    0.09
     tiltak
    0.09
     ప్రయత్న
    0.09
    ...[
    0.09
     उपाय
    0.08
     해결
    0.08
    办法
    0.08
    Activations Density 0.082%

    No Known Activations