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. 112705
    Prev
    Next
    INDEX
    Explanations

    Result

    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
    基金
    -0.08
     deficiencies
    -0.07
     deficiency
    -0.07
     Damen
    -0.07
     মন
    -0.07
     আদাল
    -0.07
     amounted
    -0.07
    -water
    -0.07
     responsables
    -0.07
    _projection
    -0.07
    POSITIVE LOGITS
     Recover
    0.09
    recover
    0.09
     recovery
    0.09
     aliv
    0.09
    Recover
    0.09
     recover
    0.08
     Του
    0.08
     recovering
    0.08
     ¥
    0.08
     Recovery
    0.08
    Activations Density 0.001%

    No Known Activations