© 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. 11-RESID-POST-AA
    11. 95561
    Prev
    Next
    INDEX
    Explanations

    ideal condition, needs

    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
    	push
    -0.08
     Simply
    -0.07
     긴
    -0.07
     σε
    -0.07
    .Be
    -0.07
    jima
    -0.07
     비
    -0.07
     全球
    -0.07
    _MESSAGE
    -0.07
    _paid
    -0.07
    POSITIVE LOGITS
     malicious
    0.11
     delinc
    0.11
     unchecked
    0.10
     attacks
    0.10
     hostile
    0.10
     saldır
    0.10
     sinister
    0.09
     undermine
    0.09
     rampant
    0.09
     unscr
    0.09
    Activations Density 0.095%

    No Known Activations