© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 25018
    Prev
    Next
    INDEX
    Explanations

    回

    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
     itiner
    -0.08
    imul
    -0.07
    ställ
    -0.07
    ificazione
    -0.07
     Ges
    -0.07
    .misc
    -0.07
     fool
    -0.07
     perfiles
    -0.07
    sgesamt
    -0.07
     बेच
    -0.07
    POSITIVE LOGITS
    ********
    0.10
    {}",
    0.08
     departmental
    0.07
    екти
    0.07
    ****
    0.07
    ירה
    0.07
     بم
    0.07
     חד
    0.07
    �
    0.07
     Dragon
    0.07
    Activations Density 0.000%

    No Known Activations