Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 130342
    Prev
    Next
    INDEX
    Explanations

    computer language

    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
     terlebih
    -0.09
     ಪ್ರಮ
    -0.08
     ಮಾಹಿತಿ
    -0.08
    aban
    -0.07
     వద్ద
    -0.07
     જાણ
    -0.07
     неабход
    -0.07
     jos
    -0.07
     Thoughts
    -0.07
    ator
    -0.07
    POSITIVE LOGITS
     Scrap
    0.08
    .Br
    0.08
    �
    0.07
    ונ
    0.07
     scrap
    0.07
     meilleur
    0.07
    .Cluster
    0.07
     Minis
    0.07
    .Dock
    0.07
    Cluster
    0.07
    Activations Density 0.051%

    No Known Activations