Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 48154
    Prev
    Next
    INDEX
    Explanations

    of

    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
     statistically
    -0.08
    ក្នុង
    -0.08
    จริง
    -0.08
     intellectually
    -0.08
     scientifically
    -0.08
    ethical
    -0.08
    antly
    -0.08
     folgen
    -0.08
     нотари
    -0.08
    အား
    -0.08
    POSITIVE LOGITS
    (sd
    0.07
     Whisper
    0.07
     विद्य
    0.07
    sd
    0.07
     Van
    0.07
    Hosts
    0.07
     Sitz
    0.07
     swallowed
    0.07
    FIT
    0.07
    Bytes
    0.07
    Activations Density 0.010%

    No Known Activations