© 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. 64874
    Prev
    Next
    INDEX
    Explanations

    protection

    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
     premios
    -0.09
    筹
    -0.09
     celebr
    -0.09
    Nearly
    -0.08
     assent
    -0.08
     вк
    -0.08
     ва
    -0.08
    方便
    -0.08
     awkward
    -0.07
     бәх
    -0.07
    POSITIVE LOGITS
     antivirus
    0.17
     Antivirus
    0.16
     spyware
    0.13
     防
    0.13
     defenses
    0.13
     Protection
    0.12
     defensive
    0.12
     Firewall
    0.12
    防
    0.12
     защиты
    0.12
    Activations Density 0.032%

    No Known Activations