Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 61011
    Prev
    Next
    INDEX
    Explanations

    back

    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
     (?
    -0.08
    (?
    -0.07
     HUGE
    -0.07
     bestimmten
    -0.07
     fua
    -0.07
     каст
    -0.07
     préalable
    -0.07
     oxidation
    -0.07
    idur
    -0.07
    erms
    -0.07
    POSITIVE LOGITS
     resilience
    0.16
     resilient
    0.15
     resil
    0.15
     rebuilt
    0.14
     rebuilding
    0.13
     reconstru
    0.13
     rebuild
    0.12
     aftermath
    0.12
     comeback
    0.12
     restructure
    0.11
    Activations Density 0.087%

    No Known Activations