© 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. 29563
    Prev
    Next
    INDEX
    Explanations

    -serif

    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
    附近
    -0.09
     Grimm
    -0.09
     notorious
    -0.08
     таза
    -0.08
     Allgeme
    -0.08
    φέ
    -0.08
    른
    -0.08
     beasts
    -0.08
     �
    -0.08
    邻
    -0.07
    POSITIVE LOGITS
    >This
    0.08
    ced
    0.07
    0.07
    лим
    0.07
    solutely
    0.07
     upside
    0.07
    ilecek
    0.07
    idity
    0.07
    elligence
    0.07
    ade
    0.07
    Activations Density 0.001%
    No Known Activations