© 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. 26046
    Prev
    Next
    INDEX
    Explanations

    code

    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
    ทั้งหมด
    -0.08
    Discuss
    -0.08
     molho
    -0.08
     practicing
    -0.08
     boating
    -0.08
    ವಾ
    -0.08
     explicar
    -0.08
    /ic
    -0.08
     arranged
    -0.07
     Discuss
    -0.07
    POSITIVE LOGITS
     afili
    0.09
     വൈക
    0.08
     기록
    0.08
    esha
    0.08
     kark
    0.08
     finne
    0.08
     STORE
    0.08
    仕
    0.07
     vanskelig
    0.07
     ham
    0.07
    Activations Density 0.000%

    No Known Activations