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. 12183
    Prev
    Next
    INDEX
    Explanations

    d

    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
     intens
    -0.07
    หล
    -0.07
     MUL
    -0.07
    oty
    -0.07
     ultras
    -0.07
     retard
    -0.07
     останов
    -0.07
    ultat
    -0.07
     balloon
    -0.07
     stunt
    -0.07
    POSITIVE LOGITS
    Nx
    0.09
     ersetzen
    0.08
     remplacer
    0.08
     отно
    0.08
     gardener
    0.08
     packaging
    0.08
     congr
    0.07
     kaps
    0.07
     applicant
    0.07
     किसान
    0.07
    Activations Density 0.006%

    No Known Activations