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. 53023
    Prev
    Next
    INDEX
    Explanations

    space and satellites

    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
     reform
    -0.08
     "../../../
    -0.08
     ../../../
    -0.08
     staff
    -0.08
     intuitive
    -0.07
     quest
    -0.07
     forh
    -0.07
     finite
    -0.07
     oly
    -0.07
     Staff
    -0.07
    POSITIVE LOGITS
     satellites
    0.11
    Satellite
    0.10
     Geburtstag
    0.10
     упаков
    0.09
     satellite
    0.09
     Registrierung
    0.09
     Sputnik
    0.09
    जह
    0.09
     sementes
    0.09
    ğraf
    0.08
    Activations Density 0.017%

    No Known Activations