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. 30726
    Prev
    Next
    INDEX
    Explanations

    structure of commands

    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
     letz
    -0.08
     zuletzt
    -0.08
    Mit
    -0.08
     Mina
    -0.07
    [Math
    -0.07
    itaire
    -0.07
     Fifth
    -0.07
    য়ে
    -0.07
     �
    -0.07
     与
    -0.07
    POSITIVE LOGITS
     đầy
    0.08
    úc
    0.08
     objectives
    0.07
     promoc
    0.07
     flotation
    0.07
     navbar
    0.07
     התק
    0.07
    ajar
    0.07
     पर्व
    0.07
    át
    0.07
    Activations Density 0.001%

    No Known Activations