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. 112024
    Prev
    Next
    INDEX
    Explanations

    Introducing a point

    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
    045
    -0.08
    -0.08
    .ie
    -0.08
     mainly
    -0.08
     avanço
    -0.08
     basically
    -0.08
     essentially
    -0.07
    023
    -0.07
    mostly
    -0.07
     -->↵
    -0.07
    POSITIVE LOGITS
     sik
    0.08
     убед
    0.08
     Clap
    0.08
     misunderstood
    0.08
     liten
    0.07
     inspiración
    0.07
    ,key
    0.07
    ៈ
    0.07
     Kremlin
    0.07
     τότε
    0.07
    Activations Density 0.007%

    No Known Activations