© 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. 11-RESID-POST-AA
    11. 30923
    Prev
    Next
    INDEX
    Explanations

    answered

    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
    ikel
    -0.08
    tal
    -0.08
     Principle
    -0.07
    arlan
    -0.07
    liegenden
    -0.07
     Cv
    -0.07
    ICIO
    -0.07
     iku
    -0.07
     Streit
    -0.07
    лана
    -0.07
    POSITIVE LOGITS
     সফল
    0.09
     favor
    0.09
     صحیح
    0.09
     positivos
    0.09
    成绩
    0.09
     موفق
    0.09
     успеш
    0.09
     favorable
    0.09
     favourable
    0.09
     correctness
    0.08
    Activations Density 0.010%

    No Known Activations