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. 55189
    Prev
    Next
    INDEX
    Explanations

    wind

    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
     invent
    -0.08
    শেষ
    -0.08
     exploração
    -0.07
     posição
    -0.07
     exploitation
    -0.07
     ইত
    -0.07
     се
    -0.07
     nect
    -0.07
     explotación
    -0.07
     выг
    -0.07
    POSITIVE LOGITS
    .Regular
    0.08
     fountain
    0.08
     trout
    0.08
    .admin
    0.08
    (Admin
    0.08
     Provincial
    0.08
    css
    0.07
    .Send
    0.07
     Admin
    0.07
    PMailer
    0.07
    Activations Density 0.001%

    No Known Activations