Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 90054
    Prev
    Next
    INDEX
    Explanations

    preloading

    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
     밖
    -0.08
     �
    -0.08
     ಬ
    -0.08
     보는
    -0.07
     ビ
    -0.07
    _contents
    -0.07
     제
    -0.07
     sendiri
    -0.07
     기존
    -0.07
    暖
    -0.07
    POSITIVE LOGITS
    signin
    0.08
     it'd
    0.08
    interest
    0.08
     וועלן
    0.07
     קענען
    0.07
     tob
    0.07
    abaw
    0.07
    vum
    0.07
     կունեն
    0.07
     sn
    0.07
    Activations Density 0.001%

    No Known Activations