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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 43075
    Prev
    Next
    INDEX
    Explanations

    SQL injection

    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
     Pare
    -0.08
    Pare
    -0.08
     Mina
    -0.08
    ेका
    -0.08
     consci
    -0.08
    207
    -0.07
     PMP
    -0.07
    Sometimes
    -0.07
     vezes
    -0.07
     definitions
    -0.07
    POSITIVE LOGITS
     attackers
    0.09
     공격
    0.09
     diretamente
    0.08
     persuasive
    0.08
     हमला
    0.08
     안전
    0.08
     veiligheids
    0.08
     kwaad
    0.08
     ആക്രമ
    0.08
     đưa
    0.08
    Activations Density 0.005%

    No Known Activations