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. 119958
    Prev
    Next
    INDEX
    Explanations

    opinions

    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
     anaer
    -0.08
    бек
    -0.08
     места
    -0.07
     bulls
    -0.07
    _Tr
    -0.07
    ंजी
    -0.07
    ясь
    -0.07
    кел
    -0.07
     туал
    -0.07
    Builder
    -0.07
    POSITIVE LOGITS
    essential
    0.09
     Essentially
    0.09
     essentially
    0.08
     swoim
    0.08
     şöyle
    0.08
    UIC
    0.08
    iert
    0.08
     basically
    0.08
    .argument
    0.08
     kritiek
    0.08
    Activations Density 0.046%

    No Known Activations