© 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. 64928
    Prev
    Next
    INDEX
    Explanations

    or/be conditional statements

    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
    တ
    -0.08
     bridge
    -0.08
     aptitude
    -0.08
     yayın
    -0.08
    的方法
    -0.08
     thu
    -0.08
    inary
    -0.07
    ٽو
    -0.07
     അവതരിപ്പ
    -0.07
     możemy
    -0.07
    POSITIVE LOGITS
     helpless
    0.09
     Constant
    0.08
     Moving
    0.08
    Constant
    0.08
     moved
    0.08
     Move
    0.08
    Moving
    0.08
     št
    0.08
     Plätze
    0.08
    ga
    0.08
    Activations Density 0.012%

    No Known Activations