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. 11-RESID-POST-AA
    6. 60746
    Prev
    Next
    INDEX
    Explanations

    l

    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
    Older
    -0.08
     Tape
    -0.08
    nds
    -0.08
     earthquakes
    -0.08
     אח
    -0.07
    clearfix
    -0.07
     affectionate
    -0.07
    Atmos
    -0.07
    (nx
    -0.07
    Checking
    -0.07
    POSITIVE LOGITS
     remarkable
    0.09
     survival
    0.08
    itar
    0.08
    ‍
    0.08
     surv
    0.08
     remarkably
    0.07
    ären
    0.07
    �
    0.07
     فران
    0.07
     bere
    0.07
    Activations Density 0.001%

    No Known Activations