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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 42035
    Prev
    Next
    INDEX
    Explanations

    TV

    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
     laaye
    -0.08
     Owl
    -0.08
     beb
    -0.08
     invented
    -0.08
     inventions
    -0.07
     Stabil
    -0.07
     eche
    -0.07
     Assim
    -0.07
    üs
    -0.07
     aeg
    -0.07
    POSITIVE LOGITS
    .email
    0.08
    Hay
    0.08
     horizonte
    0.08
    -F
    0.08
    -MM
    0.08
     económico
    0.07
    (email
    0.07
     discounted
    0.07
    -Q
    0.07
     Ritter
    0.07
    Activations Density 0.001%

    No Known Activations