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. 49036
    Prev
    Next
    INDEX
    Explanations

    床

    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
    Haus
    -0.08
     Howard
    -0.08
    _SP
    -0.08
     Creation
    -0.07
     abrasive
    -0.07
    ाएँ
    -0.07
    RARY
    -0.07
     absch
    -0.07
    นะ
    -0.07
    to
    -0.07
    POSITIVE LOGITS
    实践
    0.10
    意义
    0.09
     manifestations
    0.08
     wisdom
    0.08
     parlant
    0.08
     eclipse
    0.08
    实际
    0.08
     clín
    0.07
     الإ
    0.07
     നിന്ന
    0.07
    Activations Density 0.008%

    No Known Activations