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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 64816
    Prev
    Next
    INDEX
    Explanations

    Java keywords

    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
     अर्थात
    -0.08
     probability
    -0.08
    ây
    -0.08
     inclination
    -0.08
    urit
    -0.07
    औ
    -0.07
    つまり
    -0.07
     Implementation
    -0.07
     ഇപ്പോള്
    -0.07
     Probability
    -0.07
    POSITIVE LOGITS
     lebens
    0.08
     gəl
    0.08
    bord
    0.08
    <
    0.08
     Zh
    0.08
     mellow
    0.07
    闭
    0.07
     tópico
    0.07
     pastime
    0.07
    珍
    0.07
    Activations Density 0.003%

    No Known Activations