© 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. 3-RESID-POST-AA
    11. 13112
    Prev
    Next
    INDEX
    Explanations

    Dx

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SAFE
    -0.08
    liest
    -0.08
    ату
    -0.08
    led
    -0.07
     Vip
    -0.07
    suite
    -0.07
     مصدر
    -0.07
    rolle
    -0.07
    OGRAPH
    -0.07
    USERNAME
    -0.07
    POSITIVE LOGITS
     Mum
    0.08
     Kro
    0.08
     అ
    0.07
     már
    0.07
     coag
    0.07
    ષ
    0.07
     papier
    0.07
    ән
    0.07
    udy
    0.07
     sistem
    0.07
    Activations Density 0.001%

    No Known Activations