© 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. 108521
    Prev
    Next
    INDEX
    Explanations

    code && game logic

    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
     Lost
    -0.09
     Loss
    -0.09
     perdas
    -0.08
    .loss
    -0.08
     States
    -0.08
    =time
    -0.08
    สู
    -0.08
     barras
    -0.08
     pérdidas
    -0.08
    (loss
    -0.08
    POSITIVE LOGITS
     permissible
    0.09
    合法
    0.09
     permitted
    0.08
     eligible
    0.08
     allowed
    0.08
    _TOOLTIP
    0.08
     legal
    0.08
    Clicked
    0.08
     laman
    0.08
    Кар
    0.08
    Activations Density 0.002%

    No Known Activations