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. 78122
    Prev
    Next
    INDEX
    Explanations

    uses

    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
     이에
    -0.08
    }`
    -0.08
     ito
    -0.07
     unavoidable
    -0.07
     sd
    -0.07
    IOS
    -0.07
     necesarios
    -0.07
    amm
    -0.07
    حل
    -0.07
     veille
    -0.07
    POSITIVE LOGITS
     الأمر
    0.08
     Pil
    0.08
     आव
    0.08
    嗎
    0.07
     Pagan
    0.07
     GG
    0.07
     pewno
    0.07
     wiederum
    0.07
     pil
    0.07
     Reck
    0.07
    Activations Density 0.130%

    No Known Activations