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. 54190
    Prev
    Next
    INDEX
    Explanations

    and

    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
    Ä
    -0.08
    IPP
    -0.07
    -0.07
     monop
    -0.07
    Drive
    -0.07
    IRST
    -0.07
    .first
    -0.07
    Seb
    -0.07
     unplug
    -0.07
     triv
    -0.07
    POSITIVE LOGITS
     tailoring
    0.09
     Hirsch
    0.08
     detaill
    0.08
    мос
    0.08
    storybook
    0.08
     Detailed
    0.08
     Daytona
    0.08
    нош
    0.08
    gir
    0.08
     boutique
    0.08
    Activations Density 0.004%

    No Known Activations