© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 99329
    Prev
    Next
    INDEX
    Explanations

    Flavorful cooking ingredients

    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
     ekran
    -0.08
    数字
    -0.08
    jumlah
    -0.08
     حلول
    -0.08
    إن
    -0.08
     Invisalign
    -0.08
    数量
    -0.07
    nowrap
    -0.07
     πρέπει
    -0.07
     fungsi
    -0.07
    POSITIVE LOGITS
     fundamentals
    0.08
     foundational
    0.08
     grief
    0.08
     groundwork
    0.08
     기본
    0.07
     vague
    0.07
     Grundlagen
    0.07
     Fundamental
    0.07
    stown
    0.07
    itimate
    0.07
    Activations Density 0.028%

    No Known Activations