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

    Neuronpedia

    APICircuit 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. 7-RESID-POST-AA
    6. 130971
    Prev
    Next
    INDEX
    Explanations

    noise

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     conclu
    -0.08
     ini
    -0.08
     matrices
    -0.08
    -season
    -0.08
     Season
    -0.07
     lu
    -0.07
     coverings
    -0.07
     dobr
    -0.07
     매
    -0.07
     metaphor
    -0.07
    POSITIVE LOGITS
    杂
    0.10
     Norton
    0.08
    �
    0.08
    �
    0.07
    击
    0.07
     Salary
    0.07
    imbus
    0.07
    adio
    0.07
     unwanted
    0.07
     علينا
    0.07
    Activations Density 0.003%

    No Known Activations