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. 52994
    Prev
    Next
    INDEX
    Explanations

    fridge

    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
    atenate
    -0.08
     faszin
    -0.08
    Mont
    -0.08
     Mont
    -0.08
    _AUTHOR
    -0.08
    etak
    -0.07
     piston
    -0.07
     vak
    -0.07
    ennen
    -0.07
    дарын
    -0.07
    POSITIVE LOGITS
     keessaa
    0.08
     মঙ্গলবার
    0.08
     Thursdays
    0.07
    lh
    0.07
    みに
    0.07
    里的
    0.07
     breasts
    0.07
     থাকা
    0.07
     বুধবার
    0.07
     বৃহস্পতিবার
    0.07
    Activations Density 0.005%

    No Known Activations