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. 43289
    Prev
    Next
    INDEX
    Explanations

    Negation

    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
     Rustic
    -0.08
     asesor
    -0.07
     earning
    -0.07
     opportunity
    -0.07
    잠
    -0.07
    .Window
    -0.07
     Moreno
    -0.07
     наслаж
    -0.07
    設
    -0.07
     nekoliko
    -0.07
    POSITIVE LOGITS
     otherwise
    0.09
     või
    0.09
     autrement
    0.09
     BES
    0.08
     annars
    0.08
    无法
    0.08
     inadequate
    0.08
    submit
    0.08
     किंवा
    0.08
     muuten
    0.07
    Activations Density 0.117%

    No Known Activations