© 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. 65377
    Prev
    Next
    INDEX
    Explanations

    wear

    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
     pertinentes
    -0.07
     Yuk
    -0.07
     pener
    -0.07
     Runs
    -0.07
    	de
    -0.07
     Shock
    -0.07
     focal
    -0.07
     cpp
    -0.07
    irg
    -0.07
     Taylor
    -0.07
    POSITIVE LOGITS
     mord
    0.09
    マン
    0.09
     Hum
    0.08
     Bers
    0.08
     Mina
    0.08
    .mask
    0.07
     biopsy
    0.07
    牌
    0.07
    غان
    0.07
     humm
    0.07
    Activations Density 0.024%

    No Known Activations