© 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. 108741
    Prev
    Next
    INDEX
    Explanations

    Propaganda

    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
     menge
    -0.09
    qrst
    -0.08
    ellungen
    -0.08
     Sustain
    -0.08
     Bi
    -0.08
     refreshments
    -0.08
    otto
    -0.08
     Anforderungen
    -0.08
     Rä
    -0.08
    ově
    -0.08
    POSITIVE LOGITS
     wholesome
    0.09
     ವಿರುದ್ಧ
    0.09
     neatly
    0.09
     villain
    0.09
     wrongdoing
    0.09
     rightful
    0.08
     unmistak
    0.08
     civilized
    0.08
     folks
    0.08
     idyllic
    0.08
    Activations Density 0.053%

    No Known Activations