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. 104195
    Prev
    Next
    INDEX
    Explanations

    in

    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
    ongera
    -0.08
     öpp
    -0.08
     akut
    -0.07
     tradução
    -0.07
     acknowled
    -0.07
     توفر
    -0.07
     Sono
    -0.07
    581
    -0.07
     stock
    -0.07
    增加
    -0.07
    POSITIVE LOGITS
     shaping
    0.19
     molde
    0.16
     shape
    0.16
    -shaped
    0.16
     molded
    0.16
    塑
    0.16
     shaped
    0.15
     reshape
    0.15
    shape
    0.15
     sculpt
    0.15
    Activations Density 0.030%

    No Known Activations