© 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. 29654
    Prev
    Next
    INDEX
    Explanations

    influencing opinions

    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
     chall
    -0.08
    mets
    -0.07
    ajos
    -0.07
     comerc
    -0.07
     replied
    -0.07
     Hod
    -0.07
    ags
    -0.07
    etric
    -0.07
     NULL
    -0.07
     AD
    -0.07
    POSITIVE LOGITS
     misconceptions
    0.12
     perceptions
    0.11
     belief
    0.11
     attitudes
    0.11
     beliefs
    0.11
     informiert
    0.11
    belief
    0.11
     comportements
    0.11
     disbelief
    0.11
     misinformation
    0.10
    Activations Density 0.061%

    No Known Activations