© 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. 2729
    Prev
    Next
    INDEX
    Explanations

    up

    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
     మండ
    -0.08
     нем
    -0.08
     hoes
    -0.08
     বাক
    -0.08
     Lawson
    -0.08
     Rhône
    -0.07
     hö
    -0.07
    메일
    -0.07
     स्वी
    -0.07
     corps
    -0.07
    POSITIVE LOGITS
     Continental
    0.08
     SR
    0.07
     continue
    0.07
     транспорта
    0.07
     Eduardo
    0.07
    Continuation
    0.07
    <I
    0.07
    Elect
    0.07
     leh
    0.07
     continuation
    0.07
    Activations Density 0.002%

    No Known Activations