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. 117506
    Prev
    Next
    INDEX
    Explanations

    press releases

    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
    واره
    -0.08
     Mash
    -0.08
    Mash
    -0.07
    _MM
    -0.07
    ที่จะ
    -0.07
    .M
    -0.07
    Tour
    -0.07
     Messenger
    -0.07
     आक
    -0.07
    νο
    -0.07
    POSITIVE LOGITS
    検索
    0.10
    &s
    0.09
     layoffs
    0.09
     kullanıl
    0.08
     digunakan
    0.08
     !)
    0.08
    ნა
    0.08
    ాల్స
    0.08
     onmiddell
    0.08
     whopping
    0.08
    Activations Density 0.005%

    No Known Activations