© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 75491
    Prev
    Next
    INDEX
    Explanations

    acent

    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
     Alltag
    -0.08
    nick
    -0.07
     tinted
    -0.07
     לענ
    -0.07
     Vitamin
    -0.07
    ні
    -0.07
    ענ
    -0.07
    未
    -0.07
     brightly
    -0.07
     Analytics
    -0.07
    POSITIVE LOGITS
     regulation
    0.08
    Hamilton
    0.08
     kısm
    0.08
     policeman
    0.07
     komentar
    0.07
     درجه
    0.07
     телеф
    0.07
    IRS
    0.07
     langt
    0.07
    资格
    0.07
    Activations Density 0.004%

    No Known Activations