© 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. 2664
    Prev
    Next
    INDEX
    Explanations

    Selector

    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
    .ly
    -0.08
     Ae
    -0.08
    721
    -0.07
     ironically
    -0.07
    722
    -0.07
    rog
    -0.07
     evidently
    -0.07
    allah
    -0.07
     Mell
    -0.07
    cro
    -0.07
    POSITIVE LOGITS
    ખ
    0.08
     정
    0.07
     Penn
    0.07
    碼
    0.07
    ોને
    0.07
    ulam
    0.07
    قان
    0.07
     happened
    0.07
     primers
    0.07
    ydia
    0.07
    Activations Density 0.001%

    No Known Activations