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. 77310
    Prev
    Next
    INDEX
    Explanations

    walking past

    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
     Launcher
    -0.07
     QString
    -0.07
     quint
    -0.07
    YEAR
    -0.07
     bada
    -0.07
     Quint
    -0.07
     jugar
    -0.07
    ®.
    -0.07
     taus
    -0.07
     formatting
    -0.07
    POSITIVE LOGITS
     지나
    0.10
     encountering
    0.09
     unnoticed
    0.09
     encountered
    0.09
     encounters
    0.09
     crossroads
    0.09
     Encounter
    0.09
     знай
    0.09
    asses
    0.09
     toev
    0.08
    Activations Density 0.026%

    No Known Activations