© 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. 2595
    Prev
    Next
    INDEX
    Explanations

    Research papers

    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
     বন্ধ
    -0.09
     Allerg
    -0.08
    omain
    -0.08
     Mongolia
    -0.08
     Attempts
    -0.08
     Changes
    -0.07
     Gives
    -0.07
     Closed
    -0.07
     Mong
    -0.07
     जोड
    -0.07
    POSITIVE LOGITS
    十分
    0.08
     bigger
    0.08
     altogether
    0.07
     بهتر
    0.07
    384
    0.07
    लिए
    0.07
    être
    0.07
    "ל
    0.07
     dues
    0.07
     revival
    0.07
    Activations Density 0.000%

    No Known Activations