© 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. 19-RESID-POST-AA
    11. 102925
    Prev
    Next
    INDEX
    Explanations

    size and fit

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .setdefault
    -0.08
    ็ง
    -0.08
    亿
    -0.08
     esteemed
    -0.08
     اخلاق
    -0.08
     چیست
    -0.08
     serieus
    -0.08
    科研
    -0.08
     Reputation
    -0.08
    倫理
    -0.08
    POSITIVE LOGITS
     slightly
    0.18
     snug
    0.15
     Slight
    0.15
     légèrement
    0.15
     passend
    0.14
     diámetro
    0.14
     diamètre
    0.14
     accommodate
    0.13
    尺寸
    0.13
     oversized
    0.13
    Activations Density 0.019%

    No Known Activations