Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 42295
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    ̌
    -0.08
    /accounts
    -0.07
    _tar
    -0.07
    _height
    -0.07
     calibre
    -0.07
    紹介
    -0.07
    -employed
    -0.07
    _average
    -0.07
     жүргіз
    -0.07
     소개
    -0.07
    POSITIVE LOGITS
     rights
    0.09
     printable
    0.09
     полноцен
    0.08
    权限
    0.08
     assaults
    0.08
    Elems
    0.08
     bits
    0.08
    权益
    0.08
    _DESCRIPTOR
    0.08
    વિધ
    0.07
    Activations Density 0.004%

    No Known Activations