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. 53107
    Prev
    Next
    INDEX
    Explanations

    car

    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
     lloc
    -0.07
     kats
    -0.07
     Rov
    -0.07
     Site
    -0.07
     موقع
    -0.07
     site
    -0.07
    -0.07
     mortal
    -0.07
     tetr
    -0.07
     Located
    -0.07
    POSITIVE LOGITS
     compressor
    0.08
     ಗಳ
    0.08
     cabo
    0.08
     passenger
    0.08
    porter
    0.08
     necessidades
    0.08
    Trailer
    0.08
    ومان
    0.08
     Bala
    0.08
    communications
    0.08
    Activations Density 0.006%

    No Known Activations