© 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. 26241
    Prev
    Next
    INDEX
    Explanations

    multiple languages/technical specifications

    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
    Forgot
    -0.09
    _TYPED
    -0.08
    Prescription
    -0.08
     foreclosure
    -0.08
     Pres
    -0.08
    etail
    -0.08
    adilla
    -0.08
     לפ
    -0.07
     السلط
    -0.07
     judiciaire
    -0.07
    POSITIVE LOGITS
     kb
    0.09
     percent
    0.09
     seconds
    0.08
    percent
    0.08
    ×
    0.08
     Mbps
    0.08
     k
    0.08
    倍
    0.07
    年前
    0.07
     kredit
    0.07
    Activations Density 0.029%

    No Known Activations