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. 77181
    Prev
    Next
    INDEX
    Explanations

    code-related text

    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
     alcanzar
    -0.08
     hearings
    -0.08
    ättning
    -0.08
    ki
    -0.08
     dul
    -0.07
    (pipe
    -0.07
    .FONT
    -0.07
     அல்லது
    -0.07
     alcanza
    -0.07
    Sau
    -0.07
    POSITIVE LOGITS
     Yang
    0.08
     envia
    0.08
     dismiss
    0.08
    Yang
    0.07
     tle
    0.07
     protagon
    0.07
    重要
    0.07
     cos
    0.07
     pob
    0.07
     час
    0.07
    Activations Density 0.000%

    No Known Activations