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. 7-RESID-POST-AA
    6. 131034
    Prev
    Next
    INDEX
    Explanations

    clock frequency values

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     renk
    -0.08
     trata
    -0.08
     geop
    -0.08
     dirección
    -0.08
     deck
    -0.08
    uningdek
    -0.07
    יינים
    -0.07
     surfers
    -0.07
     extensive
    -0.07
     trattamento
    -0.07
    POSITIVE LOGITS
    MHz
    0.08
     Clark
    0.08
    _clk
    0.08
    legung
    0.08
     MHz
    0.07
    judge
    0.07
    mill
    0.07
     CLK
    0.07
    ОЛ
    0.07
    dma
    0.07
    Activations Density 0.004%

    No Known Activations