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. 29944
    Prev
    Next
    INDEX
    Explanations

    none/no

    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
     Agreement
    -0.08
    ashin
    -0.08
     Hal
    -0.07
     agreement
    -0.07
     Understanding
    -0.07
     halb
    -0.07
     Restore
    -0.07
     Row
    -0.07
     కొ
    -0.07
     Restoration
    -0.07
    POSITIVE LOGITS
     okenn
    0.12
    ,没有
    0.11
     except
    0.11
    沒有
    0.10
    ,截至
    0.10
     никаких
    0.10
    /no
    0.09
     presently
    0.09
    ucune
    0.09
     actuellement
    0.09
    Activations Density 0.068%

    No Known Activations