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. 42153
    Prev
    Next
    INDEX
    Explanations

    air

    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
     מא
    -0.08
     joke
    -0.07
     приз
    -0.07
     जैसे
    -0.07
     phone
    -0.07
     mistake
    -0.07
     роман
    -0.07
     charging
    -0.07
     crisi
    -0.07
     nằm
    -0.07
    POSITIVE LOGITS
     المرور
    0.08
    Dann
    0.08
     alrededor
    0.08
    entwicklung
    0.08
     abrasive
    0.08
     foliage
    0.07
    Around
    0.07
     السي
    0.07
     courte
    0.07
     consigue
    0.07
    Activations Density 0.007%

    No Known Activations