© 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. 26550
    Prev
    Next
    INDEX
    Explanations

    blackout

    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
     Evr
    -0.08
    ROS
    -0.08
     財
    -0.08
    buy
    -0.08
    財
    -0.08
     Hele
    -0.08
    Sint
    -0.08
    Catal
    -0.08
    iali
    -0.08
     vcs
    -0.08
    POSITIVE LOGITS
     lamp
    0.08
    _masks
    0.08
    .fade
    0.08
     curtains
    0.08
     Turner
    0.08
    遮
    0.08
    rijke
    0.08
     masking
    0.08
     ತರ
    0.07
     сна
    0.07
    Activations Density 0.002%

    No Known Activations