© 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. 54825
    Prev
    Next
    INDEX
    Explanations

    of

    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
    大道
    -0.08
     nominee
    -0.08
     н
    -0.07
    ീവ്
    -0.07
     പ്ര
    -0.07
    lecture
    -0.07
    ിച്ചത്
    -0.07
    imuth
    -0.07
    verband
    -0.07
     ਹਾਂ
    -0.07
    POSITIVE LOGITS
    Suppress
    0.07
     Quinn
    0.07
    yac
    0.07
    पास
    0.07
    baa
    0.07
     вол
    0.07
     tor
    0.07
     ब्य
    0.07
     kring
    0.07
    .hadoop
    0.07
    Activations Density 0.203%

    No Known Activations