© 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. 102917
    Prev
    Next
    INDEX
    Explanations

    2

    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
     tientallen
    -0.10
     семь
    -0.10
     honderden
    -0.09
    анды
    -0.09
     миллион
    -0.09
     پنج
    -0.09
    огда
    -0.09
     zeven
    -0.09
     সপ্ত
    -0.08
     shaving
    -0.08
    POSITIVE LOGITS
    -id
    0.09
    ेज
    0.08
    Id
    0.08
    _STANDARD
    0.08
    ىڭ
    0.08
    _id
    0.08
    िड
    0.08
    उ
    0.08
    Ich
    0.07
    uaq
    0.07
    Activations Density 0.006%

    No Known Activations