© 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. 842
    Prev
    Next
    INDEX
    Explanations

    necrosis and cell death

    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
     ench
    -0.08
    -flow
    -0.07
     Encourage
    -0.07
     ><
    -0.07
     assort
    -0.07
    Cog
    -0.07
     veuillez
    -0.07
     बढ
    -0.07
     Acoustic
    -0.07
     unterwegs
    -0.07
    POSITIVE LOGITS
     inflicted
    0.11
     devastation
    0.11
     apoptosis
    0.11
     damage
    0.10
     shock
    0.10
     повреж
    0.10
    损
    0.10
     irreversible
    0.10
     નુક
    0.10
     injury
    0.09
    Activations Density 0.014%

    No Known Activations