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. 106291
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas

    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
     دوست
    -0.09
    治疗
    -0.08
    .curr
    -0.08
    -commercial
    -0.08
    بود
    -0.08
    يدا
    -0.08
    療
    -0.08
    itories
    -0.08
     chip
    -0.08
    .bio
    -0.07
    POSITIVE LOGITS
     Fourier
    0.12
     FFT
    0.11
     computes
    0.10
    傅
    0.10
     transformation
    0.10
    _fft
    0.10
     Transformation
    0.09
     fft
    0.09
     transformación
    0.09
    FFT
    0.09
    Activations Density 0.006%

    No Known Activations