© 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. 3-RESID-POST-AA
    11. 2497
    Prev
    Next
    INDEX
    Explanations

    BGP

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Aero
    -0.08
    ไม
    -0.08
    [F
    -0.07
    ABA
    -0.07
    ก่อน
    -0.07
     Gerry
    -0.07
    idan
    -0.07
    	Field
    -0.07
     Av
    -0.07
    	field
    -0.07
    POSITIVE LOGITS
     cin
    0.08
     календар
    0.08
    ட்ச
    0.07
     limb
    0.07
    ouse
    0.07
     rég
    0.07
    وع
    0.07
     Пок
    0.07
     olnud
    0.07
     calendars
    0.07
    Activations Density 0.001%

    No Known Activations