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. 44030
    Prev
    Next
    INDEX
    Explanations

    pudd

    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
     geloof
    -0.08
     உ
    -0.08
     acredita
    -0.08
     parole
    -0.08
    allos
    -0.08
     Rotary
    -0.08
     keyword
    -0.08
     acredit
    -0.08
    tais
    -0.07
    .weight
    -0.07
    POSITIVE LOGITS
     pudd
    0.08
    rename
    0.08
     spray
    0.08
     unnoticed
    0.08
     hotspots
    0.08
     verw
    0.08
    Ren
    0.08
     пры
    0.08
     pockets
    0.08
    illés
    0.08
    Activations Density 0.001%

    No Known Activations