Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12882
    Prev
    Next
    INDEX
    Explanations

    and

    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
     Nero
    -0.08
    Jim
    -0.08
    Plant
    -0.07
    chg
    -0.07
    েক্ষ
    -0.07
    PEC
    -0.07
    .ed
    -0.07
    -м
    -0.07
    \e
    -0.07
     lec
    -0.07
    POSITIVE LOGITS
    ツ
    0.08
     suf
    0.08
    duplic
    0.07
    ambili
    0.07
    ovým
    0.07
     revenge
    0.07
     merk
    0.07
     drz
    0.07
     ricord
    0.07
    úss
    0.07
    Activations Density 0.026%

    No Known Activations