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. 52929
    Prev
    Next
    INDEX
    Explanations

    Correcting the mean

    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
    tocol
    -0.08
    blu
    -0.08
     receptors
    -0.08
    �
    -0.08
    秒速
    -0.08
     दृश्य
    -0.08
    zol
    -0.08
     सेना
    -0.07
    folg
    -0.07
    ssh
    -0.07
    POSITIVE LOGITS
     исправ
    0.12
     corrections
    0.11
     correcting
    0.11
    Correction
    0.11
     skew
    0.10
     omissions
    0.10
     corrected
    0.10
     correg
    0.09
     Corre
    0.09
    Missing
    0.09
    Activations Density 0.014%

    No Known Activations