© 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. 64408
    Prev
    Next
    INDEX
    Explanations

    shock

    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
     summertime
    -0.09
     annuelle
    -0.09
     pastime
    -0.09
    επισ
    -0.09
    楽し
    -0.09
    録
    -0.08
     voisin
    -0.08
     neighbour
    -0.08
     Ferien
    -0.08
     வருட
    -0.08
    POSITIVE LOGITS
     losses
    0.09
    formatie
    0.08
     syndrome
    0.08
     потер
    0.08
     systemic
    0.08
     casualties
    0.08
     perdas
    0.08
     critically
    0.08
     victims
    0.08
     Crisis
    0.08
    Activations Density 0.005%

    No Known Activations