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. 12303
    Prev
    Next
    INDEX
    Explanations

    -

    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
    _EOL
    -0.08
     tū
    -0.08
     Rams
    -0.07
     Ladder
    -0.07
    老人
    -0.07
    _sup
    -0.07
    ელი
    -0.07
    子
    -0.07
    ميل
    -0.07
     agh
    -0.07
    POSITIVE LOGITS
    }->{
    0.08
    ностью
    0.08
     алып
    0.08
     drei
    0.08
     прось
    0.07
     تہ
    0.07
     панели
    0.07
    范围
    0.07
     vicinity
    0.07
    }">↵
    0.07
    Activations Density 0.017%

    No Known Activations