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. 43894
    Prev
    Next
    INDEX
    Explanations

    still

    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
     zudem
    -0.08
     übrigens
    -0.08
    ólica
    -0.08
     cea
    -0.08
     Vertical
    -0.08
    acion
    -0.08
    ologies
    -0.08
    атели
    -0.07
     Laura
    -0.07
     Cock
    -0.07
    POSITIVE LOGITS
     partik
    0.07
    0.07
     فإنه
    0.07
     eminent
    0.07
     inertia
    0.07
    ।
    0.07
    �
    0.07
    異
    0.07
     tremendous
    0.07
    BZ
    0.07
    Activations Density 0.030%

    No Known Activations