© 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. 1333
    Prev
    Next
    INDEX
    Explanations

    Guard

    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
    च
    -0.08
     کارت
    -0.08
    -ब
    -0.08
     pe
    -0.07
    ಳೆ
    -0.07
     lisää
    -0.07
     acreage
    -0.07
    திர
    -0.07
    ுந்த
    -0.07
    ಚ್ಚ
    -0.07
    POSITIVE LOGITS
    ™
    0.12
    ®
    0.11
    ™,
    0.10
    ®,
    0.08
     cuba
    0.08
     trei
    0.08
     ™
    0.08
     Bring
    0.08
     ®
    0.07
     Originals
    0.07
    Activations Density 0.304%

    No Known Activations