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. 55700
    Prev
    Next
    INDEX
    Explanations

    BA

    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
    ilka
    -0.08
     shaking
    -0.08
    λιο
    -0.08
    엔
    -0.08
    기간
    -0.08
    Ontario
    -0.08
     filming
    -0.07
     పె
    -0.07
     Beteilig
    -0.07
    待
    -0.07
    POSITIVE LOGITS
    这样的
    0.09
     خپل
    0.09
    กัน
    0.08
    алт
    0.07
     O
    0.07
     saav
    0.07
     Successfully
    0.07
    _repeat
    0.07
     جميل
    0.07
    _ast
    0.07
    Activations Density 0.006%

    No Known Activations