© 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. 3-RESID-POST-AA
    6. 948
    Prev
    Next
    INDEX
    Explanations

    within

    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
    Season
    -0.08
     وق
    -0.08
     Din
    -0.07
     lied
    -0.07
    cmp
    -0.07
    Erreur
    -0.07
     hen
    -0.07
     بد
    -0.07
     Sterne
    -0.07
     males
    -0.07
    POSITIVE LOGITS
     entw
    0.09
    �
    0.08
     -------
    0.08
    佛
    0.08
    藤
    0.08
     vào
    0.08
     drowning
    0.08
    -------↵
    0.07
    .sb
    0.07
     tuin
    0.07
    Activations Density 0.018%

    No Known Activations