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. 52923
    Prev
    Next
    INDEX
    Explanations

    difference between sequences

    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
     yrs
    -0.09
     prosper
    -0.09
     sludge
    -0.08
     uranium
    -0.08
     byr
    -0.07
     prosperity
    -0.07
     "+"↵
    -0.07
    伍
    -0.07
     приб
    -0.07
     yor
    -0.07
    POSITIVE LOGITS
     количестве
    0.09
     modificaciones
    0.09
    (edit
    0.08
    .modified
    0.08
     კომპ
    0.08
     alterations
    0.08
    .edit
    0.08
    rist
    0.08
     আক্রান্ত
    0.08
     compromiso
    0.08
    Activations Density 0.007%

    No Known Activations