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. 44491
    Prev
    Next
    INDEX
    Explanations

    return

    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
    STANT
    -0.07
    جاز
    -0.07
     masu
    -0.07
     dan
    -0.07
     Philipp
    -0.07
    _break
    -0.07
     mass
    -0.07
     ancestors
    -0.07
     Rapid
    -0.07
     بلند
    -0.06
    POSITIVE LOGITS
    upd
    0.08
     센
    0.08
    :variables
    0.08
     donation
    0.08
    ktf
    0.07
     upd
    0.07
     fragr
    0.07
    藏
    0.07
    .Inventory
    0.07
     나온
    0.07
    Activations Density 0.002%

    No Known Activations