© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 16391
    Prev
    Next
    INDEX
    Explanations

    Asking for clarification

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .sqrt
    -0.09
     собой
    -0.08
     :+:
    -0.08
    .Sqrt
    -0.08
     ))
    -0.08
    ં
    -0.08
     sqrt
    -0.08
    υτό
    -0.07
    શ્ક
    -0.07
     конец
    -0.07
    POSITIVE LOGITS
     dringend
    0.10
     preferences
    0.09
     customization
    0.08
     तय
    0.08
     желательно
    0.08
    preferred
    0.08
     anges
    0.08
    preferences
    0.08
    Specify
    0.08
    Preferred
    0.08
    Activations Density 0.027%

    No Known Activations