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. 55201
    Prev
    Next
    INDEX
    Explanations

    AT commands

    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
    _archive
    -0.08
    kä
    -0.07
    "&
    -0.07
     einzel
    -0.07
    &R
    -0.07
     beating
    -0.07
     spécialis
    -0.07
    ։
    -0.07
     differing
    -0.07
     specialise
    -0.07
    POSITIVE LOGITS
     Time
    0.09
     Norske
    0.08
    cun
    0.08
     Pública
    0.08
    iencia
    0.08
     Sed
    0.08
    cepción
    0.07
     Augustine
    0.07
     Chrys
    0.07
     Jefferson
    0.07
    Activations Density 0.000%

    No Known Activations