© 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. 77960
    Prev
    Next
    INDEX
    Explanations

    angle

    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
     Emerald
    -0.08
     pioneering
    -0.08
    மிழ
    -0.08
     вих
    -0.08
     consortium
    -0.08
     wool
    -0.07
     beschäd
    -0.07
     আহত
    -0.07
     раз
    -0.07
     повече
    -0.07
    POSITIVE LOGITS
     probs
    0.08
     dakika
    0.08
    noi
    0.08
    legal
    0.07
     jackson
    0.07
     cif
    0.07
    illera
    0.07
    446
    0.07
    46
    0.07
    annet
    0.07
    Activations Density 0.002%

    No Known Activations