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. 12378
    Prev
    Next
    INDEX
    Explanations

    Revolutions problems

    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
     recurrent
    -0.08
     philosophy
    -0.07
     sized
    -0.07
     교육
    -0.07
    理念
    -0.07
     ironically
    -0.07
    Recipient
    -0.07
    교육
    -0.07
     caracter
    -0.07
     delic
    -0.07
    POSITIVE LOGITS
     Audible
    0.08
     Coil
    0.08
     moulin
    0.08
     extrusion
    0.08
     Señor
    0.08
    _ACCEL
    0.08
     būs
    0.08
     cups
    0.08
     radians
    0.08
    γχ
    0.07
    Activations Density 0.008%

    No Known Activations