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. 52854
    Prev
    Next
    INDEX
    Explanations

    curved

    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
     Signals
    -0.08
     Lewis
    -0.08
     Lus
    -0.08
    uentes
    -0.07
     сигнал
    -0.07
     synchronous
    -0.07
     wired
    -0.07
     promptly
    -0.07
     hust
    -0.07
     signals
    -0.07
    POSITIVE LOGITS
    黎
    0.08
    irada
    0.08
     maga
    0.08
    vak
    0.07
    ogal
    0.07
     видом
    0.07
     voork
    0.07
    _courses
    0.07
     :.
    0.07
     мама
    0.07
    Activations Density 0.004%

    No Known Activations