© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 108592
    Prev
    Next
    INDEX
    Explanations

    misinformation

    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
     Ness
    -0.09
    Barcelona
    -0.08
     morar
    -0.08
     Programmer
    -0.08
     metals
    -0.07
     barcos
    -0.07
     programmers
    -0.07
     programmer
    -0.07
     Barcelona
    -0.07
     betalen
    -0.07
    POSITIVE LOGITS
     misinformation
    0.19
    传播
    0.14
     vaccine
    0.12
     dissemination
    0.11
     conspiracy
    0.11
     Vaccine
    0.11
     rumors
    0.10
    ข่าว
    0.10
     harmful
    0.10
     प्रचार
    0.10
    Activations Density 0.013%

    No Known Activations