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. 45000
    Prev
    Next
    INDEX
    Explanations

    leaning and angles

    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
    申
    -0.09
     Deiner
    -0.08
     Prototype
    -0.08
     deiner
    -0.07
    首次
    -0.07
     Rise
    -0.07
     Disability
    -0.07
    配送
    -0.07
     dispense
    -0.07
    出版
    -0.07
    POSITIVE LOGITS
    กีฬา
    0.08
    Tech
    0.08
    hug
    0.08
    rypto
    0.08
     энерг
    0.07
    hyp
    0.07
    }-
    0.07
    ablemente
    0.07
    WAIT
    0.07
     wait
    0.07
    Activations Density 0.008%

    No Known Activations