© 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. 154
    Prev
    Next
    INDEX
    Explanations

    and to

    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
     continuation
    -0.08
     disparition
    -0.08
    -0.08
     주장
    -0.07
     Ung
    -0.07
    ffective
    -0.07
     число
    -0.07
     Strict
    -0.07
    elia
    -0.07
     EDGE
    -0.07
    POSITIVE LOGITS
     awhile
    0.08
     considerate
    0.08
    ण
    0.08
    Christine
    0.08
     aandacht
    0.08
    考虑
    0.08
    確認
    0.08
    Tas
    0.08
     останов
    0.08
     возле
    0.08
    Activations Density 0.015%
    No Known Activations