© 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. 79156
    Prev
    Next
    INDEX
    Explanations

    statistical analysis

    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
     perpetual
    -0.08
    催
    -0.08
    ိ
    -0.08
     stuck
    -0.08
    �
    -0.07
    chedulers
    -0.07
     weird
    -0.07
    down
    -0.07
    ophyll
    -0.07
    glob
    -0.07
    POSITIVE LOGITS
     benötigt
    0.10
     genügend
    0.10
     adequately
    0.10
     ausreichend
    0.10
     Ade
    0.10
     ausreich
    0.09
     adequate
    0.09
     Ideally
    0.09
     voldoende
    0.09
     recommandé
    0.09
    Activations Density 0.004%

    No Known Activations