© 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. 31322
    Prev
    Next
    INDEX
    Explanations

    Post WWII, especially 1947

    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
    iagn
    -0.08
    Advance
    -0.08
    _df
    -0.07
     dwa
    -0.07
    _adv
    -0.07
     earlier
    -0.07
    Ingress
    -0.07
    Adv
    -0.07
    igare
    -0.07
     omg
    -0.07
    POSITIVE LOGITS
     pós
    0.19
     post
    0.19
    .post
    0.17
    	post
    0.17
    post
    0.16
     Post
    0.16
     पोस्ट
    0.16
     postoperative
    0.16
     aftermath
    0.16
    Post
    0.15
    Activations Density 0.097%

    No Known Activations