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. 112175
    Prev
    Next
    INDEX
    Explanations

    biblical references

    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
     largos
    -0.08
    оди
    -0.08
    ost
    -0.08
    jections
    -0.07
    erno
    -0.07
    otions
    -0.07
     tones
    -0.07
    =None
    -0.07
     Adelaide
    -0.07
    otion
    -0.07
    POSITIVE LOGITS
     bagi
    0.08
     doktor
    0.08
     chop
    0.08
     चालक
    0.08
     motorcycle
    0.08
     representa
    0.08
     drivetrain
    0.08
     opdrachtgever
    0.07
     robotic
    0.07
     versterken
    0.07
    Activations Density 0.002%

    No Known Activations