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. 60681
    Prev
    Next
    INDEX
    Explanations

    chronological

    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
     nozzle
    -0.08
    illante
    -0.08
     BUS
    -0.08
    Garage
    -0.07
    Fg
    -0.07
     fryer
    -0.07
     Lov
    -0.07
    .gradle
    -0.07
    掉
    -0.07
     Herren
    -0.07
    POSITIVE LOGITS
    轴
    0.08
     HO
    0.08
    গত
    0.07
    క
    0.07
    books
    0.07
    0.07
    book
    0.07
    াগত
    0.07
     chrono
    0.07
    169
    0.07
    Activations Density 0.005%

    No Known Activations