© 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. 3-RESID-POST-AA
    11. 12890
    Prev
    Next
    INDEX
    Explanations

    Spices

    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
    イン
    -0.08
    �
    -0.08
    満
    -0.08
    週間
    -0.08
     corrente
    -0.08
    ツ
    -0.08
    ancis
    -0.07
     competente
    -0.07
    ministration
    -0.07
    .IB
    -0.07
    POSITIVE LOGITS
     ді
    0.08
    գ
    0.08
     Lew
    0.07
     Bau
    0.07
     lagt
    0.07
     furthermore
    0.07
     daim
    0.07
     Yun
    0.07
     Nä
    0.07
    otl
    0.07
    Activations Density 0.000%

    No Known Activations