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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 88249
    Prev
    Next
    INDEX
    Explanations

    able

    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
     cuda
    -0.08
    .backward
    -0.08
     довольно
    -0.08
     ο
    -0.07
    কদের
    -0.07
     množ
    -0.07
    breviation
    -0.07
     CUDA
    -0.07
    .dispose
    -0.07
     nab
    -0.07
    POSITIVE LOGITS
     sleeves
    0.08
     piles
    0.08
     vetted
    0.08
    881
    0.08
     titled
    0.08
    Compart
    0.08
     recens
    0.08
    整理
    0.08
     contenant
    0.08
    머니
    0.08
    Activations Density 0.006%

    No Known Activations