© 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. 64967
    Prev
    Next
    INDEX
    Explanations

    plus sign

    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
     نقص
    -0.08
     Dorm
    -0.07
     reservations
    -0.07
    NS
    -0.07
     noticed
    -0.07
    ň
    -0.07
     overtime
    -0.07
    hip
    -0.07
     concentrates
    -0.07
     Desert
    -0.07
    POSITIVE LOGITS
    ליך
    0.08
    ，加强
    0.08
    却
    0.08
     adv
    0.07
    /internal
    0.07
     الخير
    0.07
    slam
    0.07
    ifysgol
    0.07
     communion
    0.07
    াপাশি
    0.07
    Activations Density 0.052%

    No Known Activations